Codestin Search App

aymenhmaidiwastaken · 2026-04-07T21:23:52Z

Closes #848

Drafted the MCP security blog post covering the threat landscape around AI agent tool calls — tool poisoning, rug-pull attacks, cross-server data leakage, and over-permissioned tools with concrete attack scenarios.

Includes six practical recommendations: tool allowlisting, definition fingerprinting, argument boundary enforcement, human-in-the-loop for sensitive ops, runtime monitoring, and trust domain isolation.

Happy to revise based on feedback!

github-actions · 2026-04-07T21:24:45Z

Welcome to the Agent Governance Toolkit! Thanks for your first pull request.
Please ensure tests pass, code follows style (ruff check), and you have signed the CLA.
See our Contributing Guide.

github-actions · 2026-04-07T21:24:57Z

🤖 AI Agent: contributor-guide — 🌟 What You Did Well

Hi @aymenhmaidiwastaken! 👋

Welcome to the Agent Governance Toolkit community, and thank you for contributing your time and expertise! 🎉 Your blog post draft is incredibly thoughtful and well-researched — it's clear you've put a lot of effort into breaking down complex security concepts into actionable advice. Let's dive into the review!

🌟 What You Did Well

Clarity and Structure: Your blog post is exceptionally well-organized. The "Threat Surface" and "Practical Recommendations" sections are easy to follow and provide a logical flow from problem to solution.
Actionable Advice: The six recommendations are practical, detailed, and immediately useful for readers. The inclusion of YAML examples and JSON schemas is a great touch to make the concepts tangible.
Real-World Scenarios: The attack scenarios you described are both realistic and compelling. They help illustrate the risks in a way that will resonate with practitioners.
Community Alignment: Your post aligns perfectly with the goals of this repository — promoting secure and responsible agent governance. The tie-ins to OWASP and the MCP Trust Guide are excellent.

🛠 Suggestions for Improvement

Here are a few areas where we can refine your contribution to align with project conventions and ensure maximum impact:

1. File Placement

Blog posts in this repository are typically placed under packages/{name}/docs/blog/. You've done this correctly by placing the file in packages/agent-mesh/docs/blog/. ✅
However, could you also add a test case to ensure the blog post renders correctly in our documentation pipeline? Tests for this package should go in packages/agent-mesh/tests/. You can create a simple test to verify the file's presence and formatting.

2. Linting

We use ruff for linting with a focus on E, F, and W error codes. While your blog post is Markdown and won't be linted directly, make sure any Python code snippets (like the MCP Security Scanner link) adhere to PEP 8 standards. If you include runnable Python examples in the future, running ruff locally will help catch issues early.

3. Commit Message

We follow the Conventional Commits standard for commit messages. Your commit message should start with a prefix like docs: to indicate the type of change. For example:
```
docs: add MCP security blog post on tool call firewalls
```
This helps maintainers quickly understand the purpose of your changes and ensures consistent commit history.

4. Security-Sensitive Content

Since this blog post discusses security-sensitive topics, it will receive extra scrutiny. You've done a great job referencing OWASP and providing concrete examples, but it would be helpful to link directly to the OWASP Top 10 for LLMs for readers who want to dive deeper.

5. Cross-Referencing Internal Resources

You’ve already linked to the MCP Trust Guide and the MCP Security Scanner. Great job! To make this even more robust, consider adding a link to our CONTRIBUTING.md file for readers who might want to contribute to the toolkit after reading your post.

🔗 Helpful Resources

Here are some resources to help you refine your contribution:

CONTRIBUTING.md: Guidelines for contributing to this repository.
QUICKSTART.md: A quick guide to getting started with the Agent Governance Toolkit.
OWASP Top 10 for LLMs: A great resource for understanding AI-specific security risks.

✅ Next Steps

Address the feedback above:
- Add a test case for the blog post in packages/agent-mesh/tests/.
- Ensure your commit message follows the docs: prefix convention.
- Optionally, add a link to the OWASP Top 10 for LLMs.
Push your changes to this branch. Once updated, our CI/CD pipeline will automatically re-run checks.
Let us know if you have any questions or need clarification on any of the feedback!

Once you've made these updates, we'll review your PR again and work towards merging it. Thank you for helping us make the Agent Governance Toolkit even better! 🚀

Looking forward to your updates! 😊

github-actions

🤖 AI Agent: code-reviewer

Feedback on Pull Request: blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall

🔴 CRITICAL

Tool Description Injection Vulnerability
The blog correctly highlights the risk of tool poisoning via description injection but does not explicitly recommend sanitizing tool descriptions before they are consumed by the agent. This is a critical omission because malicious descriptions can bypass LLM safeguards.
Actionable Recommendation: Add explicit guidance to sanitize tool descriptions for hidden instructions or malicious payloads before they are presented to the agent. This could include stripping non-visible characters, detecting prompt injection patterns, and validating descriptions against a whitelist of allowed patterns.
Cross-Server Data Leakage
While the blog mentions the risk of cross-server data leakage, it does not provide concrete implementation details for tracking data provenance across tool calls. Without this, the recommendation for isolating MCP server trust domains lacks actionable guidance.
Actionable Recommendation: Include technical details on how to implement data provenance tracking, such as tagging data with metadata about its origin and enforcing policies based on these tags.

🟡 WARNING

Backward Compatibility of Tool Fingerprinting
The recommendation to fingerprint tool definitions and block tools with changed definitions could lead to breaking changes in production environments. If an MCP server updates a tool description or schema for legitimate reasons (e.g., bug fixes or feature enhancements), agents may fail to function unless the fingerprints are updated.
Actionable Recommendation: Suggest implementing a staged approval process for fingerprint changes, where updates are flagged but not immediately blocked. This allows operators to review and approve legitimate changes without disrupting production.

💡 SUGGESTIONS

Expand Human-in-the-Loop Guidance
The blog mentions human approval for sensitive operations but does not specify how this could be implemented in practice.
Actionable Recommendation: Provide examples of how to integrate human-in-the-loop mechanisms, such as using a webhook to trigger approval workflows in tools like Slack or Microsoft Teams.
Runtime Monitoring Details
The recommendation for runtime monitoring is high-level and does not specify what tools or frameworks could be used to implement anomaly detection.
Actionable Recommendation: Suggest specific technologies or libraries (e.g., OpenTelemetry for tracing, Elasticsearch for log analysis) that can be used to implement runtime monitoring.
OWASP Agentic Top 10 Mapping
While the blog references ASI01 (Prompt Injection), it could benefit from mapping the other threats (rug-pull attacks, data leakage, over-permissioned tools) to relevant OWASP Agentic Top 10 categories.
Actionable Recommendation: Expand the OWASP mapping to include ASI02 (Supply Chain Vulnerabilities) for rug-pull attacks and ASI03 (Data Leakage) for cross-server data leakage.
Tool Allowlist Implementation
The YAML example for tool allowlisting is helpful but lacks details on how this policy would be enforced programmatically.
Actionable Recommendation: Provide a code snippet or pseudocode demonstrating how the allowlist can be integrated into the agent's runtime logic.
Clarify "Excessive Data Volume" Detection
The blog mentions scanning arguments for excessive data volume but does not define thresholds or criteria for what constitutes "excessive."
Actionable Recommendation: Add guidance on setting thresholds based on tool schema expectations, such as maximum string lengths or array sizes.
Link to MCP Trust Guide and Security Scanner
The blog links to the MCP Trust Guide and Security Scanner but does not summarize their functionality or relevance to the recommendations.
Actionable Recommendation: Briefly describe what these resources provide and how they can help implement the defenses outlined in the blog.

General Observations

The blog is well-written and provides a clear overview of the MCP threat landscape. It effectively communicates the urgency of securing tool calls and offers practical recommendations.
The inclusion of real-world attack scenarios is excellent and helps illustrate the risks.
The blog aligns well with the goals of the repository and contributes valuable insights to the community.

Final Recommendation

Merge the pull request after addressing the critical issues and warnings. Consider incorporating the suggestions to further enhance the blog's utility and actionable guidance.

github-actions · 2026-04-07T21:24:59Z

🤖 AI Agent: security-scanner — Security Review of PR: "MCP Security — Why Your AI Agent Tool Calls Need a Firewall"

Security Review of PR: "MCP Security — Why Your AI Agent Tool Calls Need a Firewall"

This PR introduces a blog post discussing the security implications of the Model Context Protocol (MCP) and provides practical defenses against various attack vectors. While the PR is primarily documentation, it includes code snippets and recommendations that could influence how users implement security measures. Below is a security review based on the specified criteria:

1. Prompt Injection Defense Bypass

Rating: 🔴 CRITICAL
Attack Vector: The blog post highlights a significant vulnerability in MCP: tool descriptions can be used as a vector for prompt injection attacks. An attacker could embed hidden instructions in the description field of a tool, which the LLM would interpret as trusted context. This could lead to unauthorized tool calls, data exfiltration, or other malicious behavior.
Fix: The blog post provides a solid set of recommendations for mitigating this risk, including scanning tool descriptions for imperative directives, cross-tool references, invisible Unicode, encoded payloads, and hidden instructions in comments. However, the regex-based approach in the provided code snippet is insufficient for comprehensive detection. A more robust solution would involve integrating a dedicated prompt injection detection library or model, such as OpenAI's moderation API or a custom fine-tuned LLM.

2. Policy Engine Circumvention

Rating: 🟠 HIGH
Attack Vector: The blog post identifies the risk of "rug-pull attacks," where an MCP server can modify tool definitions after they have been approved. This could allow attackers to bypass policy checks by changing the behavior of a previously approved tool.
Fix: The recommendation to use fingerprinting for tool definitions is a strong mitigation. However, the blog post should emphasize the importance of securing the storage of these fingerprints (e.g., using a secure database with access controls) and ensuring that the fingerprinting process itself is tamper-proof. Additionally, the blog could suggest periodic audits of tool definitions to detect unauthorized changes.

3. Trust Chain Weaknesses

Rating: 🟡 MEDIUM
Attack Vector: The blog does not explicitly address trust chain weaknesses, such as the lack of cryptographic validation for MCP server identities or tool definitions. This could allow attackers to impersonate trusted servers or tools.
Fix: The blog should recommend implementing cryptographic signing for tool definitions and server identities, using standards like SPIFFE/SVID or Ed25519. This would ensure that only trusted servers can publish tool definitions and that these definitions cannot be tampered with.

4. Credential Exposure

Rating: 🟠 HIGH
Attack Vector: The blog highlights the risk of sensitive data (e.g., credentials, PII) being exfiltrated through tool arguments. This is particularly concerning in multi-server deployments where data from one server could be passed to another without proper boundary enforcement.
Fix: The proposed defenses, such as argument boundary enforcement, PII detection, and provenance tracking, are strong. However, the blog should also emphasize the importance of encrypting sensitive data at rest and in transit, as well as securely managing API keys and other credentials.

5. Sandbox Escape

Rating: 🔵 LOW
Attack Vector: The blog does not directly address sandbox escape vulnerabilities. However, the focus on runtime monitoring and argument validation indirectly mitigates some risks associated with executing untrusted code or commands.
Fix: While not the focus of this blog, it would be beneficial to mention the importance of running MCP servers and tools in isolated environments (e.g., containers with strict resource limits) to prevent potential sandbox escapes.

6. Deserialization Attacks

Rating: 🟡 MEDIUM
Attack Vector: The blog does not explicitly discuss the risk of deserialization attacks, which could occur if an MCP server or tool processes untrusted serialized data. This is a common attack vector in systems that handle JSON, YAML, or other serialized formats.
Fix: The blog should include a recommendation to validate and sanitize all deserialized data, using libraries that enforce strict schema validation (e.g., pydantic or jsonschema).

7. Race Conditions

Rating: 🟡 MEDIUM
Attack Vector: The blog mentions the risk of tool definitions changing between sessions or calls, which could be exploited in a race condition. For example, an attacker could modify a tool's schema after it has been approved but before it is used.
Fix: The fingerprinting mechanism is a good start, but the blog should also recommend implementing atomic operations for fetching and validating tool definitions to prevent time-of-check-to-time-of-use (TOCTOU) vulnerabilities.

8. Supply Chain

Rating: 🔴 CRITICAL
Attack Vector: The blog identifies the risk of supply chain attacks, such as tool impersonation via typosquatting or malicious updates to third-party MCP servers. These attacks could introduce compromised tools into an agent's environment.
Fix: The blog should explicitly recommend verifying the integrity and authenticity of MCP servers and tool definitions. This could include using a registry of trusted MCP servers, implementing cryptographic signing, and conducting regular audits of third-party dependencies.

Additional Observations:

Code Snippets: The provided code snippets are generally well-written and align with best practices. However, the blog should include disclaimers that these are simplified examples and may require additional hardening for production use.
Documentation Scope: While the blog is comprehensive, it could benefit from a more explicit discussion of how these defenses integrate with the Agent Governance Toolkit. For example, it could link to specific modules or features in the toolkit that implement these defenses.
Dependency Management: The blog does not discuss the risk of dependency confusion or typosquatting in the context of MCP server implementations. This could be an important addition to the "Supply Chain" section.

Summary of Findings:

Prompt injection defense bypass: 🔴 CRITICAL
- Fix: Use robust prompt injection detection mechanisms beyond regex.
Policy engine circumvention: 🟠 HIGH
- Fix: Emphasize secure storage of fingerprints and periodic audits.
Trust chain weaknesses: 🟡 MEDIUM
- Fix: Recommend cryptographic signing for tool definitions and server identities.
Credential exposure: 🟠 HIGH
- Fix: Emphasize encryption and secure credential management.
Sandbox escape: 🔵 LOW
- Fix: Mention containerization and resource isolation for MCP servers.
Deserialization attacks: 🟡 MEDIUM
- Fix: Recommend strict schema validation for deserialized data.
Race conditions: 🟡 MEDIUM
- Fix: Suggest atomic operations for fetching and validating tool definitions.
Supply chain: 🔴 CRITICAL
- Fix: Recommend trusted server registries, cryptographic signing, and dependency audits.

Recommendations:

Enhance Prompt Injection Defenses: Integrate advanced prompt injection detection tools or models.
Strengthen Trust Chains: Include cryptographic validation for MCP servers and tool definitions.
Expand Supply Chain Security: Address dependency-related risks and emphasize the importance of trusted server registries.
Improve Documentation: Provide more explicit links to relevant modules in the Agent Governance Toolkit for implementing the recommended defenses.

This blog post is a valuable addition to the repository, but it should incorporate the above recommendations to ensure comprehensive security coverage.

imran-siddique

Thanks for writing about MCP security @aymenhmaidiwastaken! Great content. Two items before we can merge:

Sign the CLA — the license/cla check is still pending. Follow the bot instructions.
Publish the blog externally — per issue #848, the deliverable is a published post on Dev.to/Medium/Hashnode. Please publish the article there, then update the COMMUNITY.md link to point to the published URL instead of the in-repo path.

The content quality is excellent — looking forward to getting this merged once published!

aymenhmaidiwastaken · 2026-04-08T09:43:04Z

@microsoft-github-policy-service agree

aymenhmaidiwastaken · 2026-04-08T09:43:15Z

Thanks for the review @imran-siddique! Really appreciate the feedback.

I'll work on both items:

CLA — just signed it above
Publishing externally — I'll publish the article on Dev.to and update the COMMUNITY.md link to point there instead of the in-repo path. Will push the update once it's live.

Also, the AI code reviewer raised some solid points — I'll incorporate the critical ones (sanitizing tool descriptions, data provenance tracking details) and the OWASP Agentic Top 10 mapping before publishing. Should make the article stronger.

Will update the PR shortly!

imran-siddique · 2026-04-08T15:56:46Z

Great, thanks @aymenhmaidiwastaken! Take your time with the publishing. Once the blog is live and CLA is signed, ping us and we'll merge right away.

aymenhmaidiwastaken · 2026-04-08T23:17:42Z

Updated the blog post with all the reviewer feedback incorporated:

Added tool description sanitization guidance with a scan_description() implementation covering imperative directives, cross-tool references, invisible Unicode, encoded payloads, and HTML comments
Added data provenance tracking with a ProvenanceTracker class and check_boundary() enforcement
Mapped all threats to OWASP Agentic Top 10 (ASI01 for tool poisoning, ASI02 for rug-pull attacks, ASI03 for data leakage)
Added concrete human-in-the-loop implementation with Slack/Teams webhook approval and YAML policy config
Added specific monitoring stack recommendations (OpenTelemetry for tracing, Elasticsearch/Loki for logs, Grafana/Datadog/PagerDuty for alerting) with span attributes
Defined thresholds for excessive data volume (5KB warn, 20KB block, 10x median always block)
Added descriptions of the MCP Trust Guide's four governance layers and the Security Scanner's capabilities

I'll publish this on Dev.to and update the COMMUNITY.md link once it's live. Working on that now.

github-actions

🤖 AI Agent: code-reviewer

Review Feedback for Pull Request: MCP Security Blog Post

🔴 CRITICAL: Security Concerns

Tool Description Sanitization Pipeline:
- The sanitization pipeline proposed in the blog post relies heavily on regex-based matching for detecting malicious patterns in tool descriptions. While regex can catch obvious cases, it is insufficient for detecting sophisticated prompt injection attacks that leverage advanced obfuscation techniques. Consider integrating a more robust NLP-based classifier trained on adversarial examples to detect hidden instructions in tool descriptions.
Provenance Tracker Implementation:
- The ProvenanceTracker implementation uses SHA-256 for content hashing, which is insufficient for detecting partial matches or modified data. Attackers can easily bypass this by slightly altering the data. Consider using fuzzy hashing techniques like ssdeep or MinHash for more robust content similarity detection.
Cross-Domain Policies:
- The example policy for cross-domain data flow allows exceptions for specific tools like translate_text. This introduces a potential attack vector where malicious actors could exploit the exception to exfiltrate sensitive data. Ensure that exceptions are tightly scoped and include additional safeguards such as content classification, size limits, and PII detection.
Human-in-the-Loop Approval:
- The webhook-based approval mechanism lacks authentication and authorization checks. An attacker could potentially spoof approval requests or responses. Ensure that the webhook endpoint is secured using cryptographic signatures, and validate responses using a secure mechanism (e.g., HMAC or JWT).
Telemetry Logging:
- While the blog post recommends logging tool calls with full arguments, this approach may inadvertently log sensitive data (e.g., PII, credentials). Ensure that sensitive data is redacted or encrypted before being logged to prevent accidental exposure.

🟡 WARNING: Potential Breaking Changes

Tool Allowlisting:
- The proposed allowlist mechanism introduces a breaking change to how agents interact with MCP servers. If implemented, agents will no longer be able to dynamically discover tools, which could impact existing workflows. Ensure that this change is documented and communicated clearly to users, along with migration guidance.
Fingerprinting Tool Definitions:
- The fingerprinting mechanism requires MCP servers to maintain consistent tool definitions across sessions. Any server-side changes to tool definitions will now result in blocked tool calls, which could disrupt production systems. Provide a fallback mechanism or alerting system to handle such cases gracefully.

💡 SUGGESTIONS: Improvements

Structured Telemetry:
- The blog post recommends using OpenTelemetry for monitoring tool calls. Extend this recommendation to include distributed tracing across MCP servers to track data flow between trust domains. This will provide better visibility into cross-server interactions.
Runtime Argument Validation:
- The argument boundary enforcement mechanism could benefit from integrating a dedicated library for sensitive data detection, such as Microsoft Presidio or Pydantic validators. This would improve accuracy and reduce false positives.
Sandboxing Tool Execution:
- The blog post does not address sandboxing for tools that execute code (e.g., execute_command). Consider recommending the use of containerization (e.g., Docker, Firecracker) or syscall filtering (e.g., seccomp) to isolate tool execution environments.
Backward Compatibility:
- For organizations with existing MCP deployments, provide a migration guide for implementing the proposed defenses incrementally. This could include a phased rollout plan for allowlisting, fingerprinting, and provenance tracking.
OWASP Agentic Top 10 Mapping:
- The blog post provides a good mapping to OWASP Agentic Top 10 categories but could benefit from a more detailed explanation of how each recommendation mitigates specific risks. Consider adding a table summarizing the defenses against each OWASP category.

Summary

This blog post provides a comprehensive overview of the security challenges in MCP-based AI agent deployments and proposes actionable defenses. However, the implementation details for some defenses (e.g., sanitization, provenance tracking) require refinement to address sophisticated attack vectors. Additionally, the proposed changes may introduce breaking changes for existing deployments, which should be carefully documented and communicated.

Recommendations

Address the critical security concerns flagged above, particularly around sanitization, provenance tracking, and webhook approval mechanisms.
Provide detailed migration guidance for users adopting the proposed defenses.
Consider extending the blog post to include sandboxing recommendations and distributed tracing for cross-server interactions.

This blog post is a valuable addition to the repository's documentation and aligns well with the project's focus on security and governance.

aymenhmaidiwastaken · 2026-04-08T23:23:31Z

Both items addressed:

CLA — signed
Published externally — article is live on Dev.to: https://dev.to/aymenhmaidi/mcp-security-why-your-ai-agents-tool-calls-need-a-firewall-3h48

Updated COMMUNITY.md to point to the published URL instead of the in-repo path. Ready for re-review!

github-actions

🤖 AI Agent: code-reviewer

Review Summary

This blog post provides a comprehensive overview of the security risks associated with the Model Context Protocol (MCP) and offers actionable recommendations for mitigating these risks. The post is well-written, informative, and aligns with the goals of the repository. However, there are areas that could benefit from additional clarity, technical refinement, and alignment with best practices.

🔴 CRITICAL: Security Issues

Tool Description Sanitization Pipeline:
- The regex-based sanitization approach is prone to false negatives and may miss sophisticated prompt injection attempts. For example, adversaries could use obfuscated or encoded payloads that bypass simple regex checks.
- Recommendation: Integrate a more robust NLP-based classifier trained on a dataset of malicious and benign tool descriptions. Consider leveraging pre-trained models for detecting adversarial instructions.
Provenance Tracking Implementation:
- The current implementation of ProvenanceTracker relies on exact SHA-256 hash matching, which is brittle and prone to false negatives when data is slightly modified (e.g., whitespace changes, re-encoding). This could allow attackers to bypass provenance checks.
- Recommendation: Replace exact hash matching with content fingerprinting techniques, such as rolling hashes or MinHash, to improve resilience against minor modifications.
Cross-Domain Data Leakage:
- While the blog mentions the importance of provenance tracking and trust domain isolation, the example implementation does not address how to handle nested or derived data (e.g., data transformations or aggregations). This could lead to leakage of sensitive information across trust boundaries.
- Recommendation: Implement recursive provenance tracking for derived data. For example, if data from Server A is transformed and used in a tool call to Server B, the governance layer should still enforce the original trust boundary.
Human-in-the-Loop Approval:
- The webhook-based approval mechanism assumes that the human operator can make an informed decision based on the provided arguments. However, sensitive data (e.g., PII or credentials) may still be exposed in the approval request itself.
- Recommendation: Redact sensitive data from the approval request before sending it to the human operator. Use a secure channel for approvals and ensure that the request payload is encrypted.

🟡 WARNING: Potential Breaking Changes

Tool Fingerprinting:
- Introducing fingerprinting for tool definitions may break backward compatibility for existing deployments that dynamically discover tools without validation. This could lead to blocked tool calls in production environments.
- Recommendation: Provide a migration guide for existing users, including steps to generate fingerprints for currently approved tools and handle discrepancies during runtime.
Argument Boundary Enforcement:
- Enforcing strict thresholds for argument sizes and patterns may cause legitimate tool calls to be blocked, especially in edge cases where larger payloads are expected (e.g., processing large documents).
- Recommendation: Allow configurable thresholds and provide detailed logs for blocked calls to help operators fine-tune policies.

💡 Suggestions for Improvement

OWASP Agentic Top 10 Mapping:
- The blog maps threats to OWASP Agentic Top 10 categories but does not provide direct links to the OWASP documentation. Adding links would improve accessibility and credibility.
Code Examples:
- The code examples are helpful but could benefit from additional comments explaining key decisions and trade-offs. For example, the provenance tracker could include comments about why certain fields (e.g., sensitivity) are chosen.
Telemetry Recommendations:
- The OpenTelemetry setup is a good starting point, but consider adding examples of how to integrate with popular observability platforms like Datadog or Prometheus. This would make it easier for users to adopt the recommendations.
Real-World Case Studies:
- The blog would be even more impactful if it included real-world case studies or examples of MCP-related security incidents. This would help readers understand the urgency of implementing the recommended defenses.
Tool Allowlist YAML Example:
- The YAML example for tool allowlisting is clear but could include comments explaining the rationale behind each rule. For instance, why certain tools are denied for specific agent roles.
Markdown Formatting:
- Consider adding a table of contents at the beginning of the blog post for easier navigation, especially given its length.

Final Recommendation

Merge the pull request after addressing the critical security issues and warnings. The blog post is a valuable addition to the repository's documentation and provides actionable insights for securing MCP-based agent deployments.

imran-siddique · 2026-04-08T23:31:05Z

Review: APPROVE (pending rebase) ✅

Diff reviewed — 2 files: COMMUNITY.md entry + new blog post at packages/agent-mesh/docs/blog/mcp-security-firewall.md (404 lines). Closes #848.

Content review: Excellent, technically sound blog covering MCP threat surface — tool poisoning (ASI01), rug-pull attacks (ASI02), cross-server data leakage (ASI03), over-permissioned tools. Includes 6 practical defenses with concrete code examples and YAML configs. Well-structured with real attack scenarios.

Security checklist:

No eval(), exec(), pickle, shell=True, innerHTML in code examples
Code examples use standard libraries only (hashlib, json, re, httpx, asyncio)
Slack webhook URL is a placeholder (https://hooks.slack.com/workflows/T.../A.../...) — not a real secret
No hardcoded API keys or tokens
Scope matches description — blog post + COMMUNITY.md entry only
Additions > 0 (405 additions)

Before merging, please:

Rebase your branch — there are merge conflicts with current main (mergeable_state: dirty)
Fork workflows need approval in the Actions tab (Maintainer approval gate)

Great contribution! 🎉

imran-siddique

Content review passed — excellent MCP security blog post. Approving.

Author: please rebase to resolve merge conflicts, then this can merge.

aymenhmaidiwastaken · 2026-04-08T23:45:10Z

Rebased on latest main — merge conflict in COMMUNITY.md resolved. Should be good to merge now!

github-actions

🤖 AI Agent: code-reviewer

Feedback on Pull Request: MCP Security Blog Post

🔴 CRITICAL: Security Concerns

Tool Description Sanitization Pipeline
- The sanitization pipeline for tool descriptions is a good start, but regex-based detection alone is insufficient for robust security. Attackers can craft adversarial descriptions that bypass simple regex patterns. Consider integrating a machine learning-based prompt injection classifier trained on adversarial examples to complement the regex checks.
Provenance Tracking Implementation
- The ProvenanceTracker implementation uses SHA-256 for exact content matching. This approach is vulnerable to partial data leakage (e.g., substring matches or modified data). Use rolling hashes or MinHash for approximate matching to detect partial overlaps and ensure robust provenance tracking.
Cross-Server Data Leakage
- The blog mentions provenance tracking but does not address cryptographic integrity verification for cross-server data flows. Without cryptographic signatures, provenance tags can be tampered with. Consider signing provenance tags using Ed25519 or similar cryptographic methods to ensure integrity.
Human-in-the-Loop Approval
- The human approval mechanism relies on external communication tools like Slack or Teams. If these tools are compromised, attackers could spoof approval responses. Implement cryptographic signatures for approval responses to ensure authenticity.

🟡 WARNING: Potential Breaking Changes

Tool Fingerprinting
- Introducing tool fingerprinting as a runtime check may break existing integrations if servers dynamically update tool definitions. Ensure backward compatibility by allowing a grace period for server updates or providing a migration path for existing deployments.
Argument Boundary Enforcement
- Enforcing strict thresholds for argument sizes and patterns could lead to false positives in legitimate use cases. Provide clear documentation and configuration options for users to customize thresholds based on their specific needs.

💡 Suggestions for Improvement

Telemetry and Monitoring
- The OpenTelemetry integration is a strong addition. Enhance it by including error codes or reasons for blocked tool calls in the telemetry data. This will help operators diagnose issues faster.
Trust Domain Isolation
- The trust domain isolation mechanism is well-designed but could benefit from more granular policies. For example, allow specific tools to cross domains only under certain conditions (e.g., time-based restrictions or user-specific overrides).
Documentation
- The blog post references the MCP Trust Guide and MCP Security Scanner but does not provide direct links to their GitHub pages or installation instructions. Add these links for easier access.
Code Examples
- The code snippets are helpful but could be expanded with unit tests or examples of expected input/output. This would make it easier for readers to understand how to implement the solutions.
OWASP Agentic Top 10 Mapping
- The blog does a great job of mapping threats to OWASP Agentic Top 10 categories. Consider adding a summary table that lists each threat, its corresponding OWASP category, and the recommended defense.
Community Engagement
- Encourage community contributions by adding a call-to-action for readers to share their own security practices or contribute to the MCP Security Scanner module.

Overall Assessment

This blog post is a comprehensive and well-written piece that addresses critical security concerns in MCP-based agent deployments. It provides actionable recommendations and practical code examples, making it highly valuable for the community. However, there are critical areas that need stronger defenses, especially around cryptographic integrity and adversarial detection.

Recommended Actions

Integrate cryptographic integrity checks for provenance tags and human approvals.
Enhance the sanitization pipeline with machine learning-based classifiers.
Expand documentation with direct links and installation instructions for referenced tools.
Provide a migration path for existing deployments to adapt to new security features.

Let me know if you need further clarification or additional feedback!

imran-siddique · 2026-04-11T15:38:33Z

@aymenhmaidiwastaken This PR has merge conflicts. The base branch has moved forward. Please rebase onto latest main to resolve conflicts. You can run: git fetch upstream && git rebase upstream/main then force-push. Once rebased, we will merge promptly.

…Calls Addresses microsoft#848. Covers MCP threat surface (tool poisoning, rug-pull attacks, cross-server data leakage, over-permissioned tools), real attack scenarios, and practical defenses including tool allowlisting, definition fingerprinting, argument boundary enforcement, and runtime monitoring.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

aymenhmaidiwastaken · 2026-04-11T18:02:02Z

Rebased onto latest main — conflict in COMMUNITY.md resolved. Ready to merge!

github-actions

🤖 AI Agent: code-reviewer

Review Feedback for Pull Request: MCP Security Blog Post

This blog post provides a comprehensive overview of the security challenges surrounding MCP (Model Context Protocol) and offers actionable defenses. The content is well-written, technically accurate, and aligns with the goals of the repository. Below are detailed comments and feedback:

🔴 CRITICAL: Security Issues

Tool Description Sanitization Pipeline
- The sanitization logic provided in the blog post is a good starting point, but regex-based detection of prompt injection patterns is insufficient for production-grade security. Attackers can use obfuscation techniques to bypass regex rules. Consider integrating a more robust NLP-based classifier trained specifically to detect adversarial instructions in text.
- Action: Enhance the sanitization pipeline by incorporating a machine learning model trained on adversarial examples, or use existing libraries like OpenAI's moderation API for detecting harmful content.
Provenance Tracking
- The proposed ProvenanceTracker implementation is a good start but lacks cryptographic guarantees. An attacker could tamper with the provenance metadata stored in memory.
- Action: Use cryptographic signatures (e.g., HMAC with a secret key) to sign provenance tags. This ensures that any tampering with the metadata can be detected.
Cross-Server Data Leakage
- The blog post correctly identifies the risk of data leakage across trust domains but does not address sandbox escape vectors. If an MCP server is compromised, it could exploit vulnerabilities in the agent's runtime environment to bypass provenance checks.
- Action: Ensure that the governance layer operates in a sandboxed environment with strict syscall filtering (e.g., using seccomp or containerization).
Human-in-the-Loop Approval
- The Slack/Teams webhook implementation assumes that the webhook endpoint is secure. If the endpoint is exposed, attackers could spoof approval requests.
- Action: Authenticate webhook requests using a shared secret or OAuth tokens. Additionally, log all approval decisions for audit purposes.

🟡 WARNING: Potential Breaking Changes

Tool Fingerprinting
- The fingerprinting mechanism proposed (hashlib.sha256) assumes that tool definitions are deterministic. If MCP servers introduce non-deterministic fields (e.g., timestamps or random IDs), the fingerprints will break.
- Action: Ensure that the fingerprinting logic explicitly excludes non-deterministic fields from the hash computation.
Argument Boundary Enforcement
- The enforcement of argument size limits and patterns may cause existing agents to fail if they rely on large payloads or previously allowed patterns.
- Action: Introduce these policies incrementally and provide clear documentation for developers to adapt their agents.

💡 SUGGESTIONS: Improvements

Telemetry with OpenTelemetry
- The OpenTelemetry instrumentation is well-designed, but consider adding support for distributed tracing across MCP servers. This would allow operators to trace the flow of data across multiple servers and identify bottlenecks or suspicious patterns.
- Action: Use OpenTelemetry's SpanContext to propagate trace IDs across tool calls.
Least Privilege for Tools
- The blog post suggests maintaining an allowlist for tools, but this approach can become cumbersome for large-scale deployments with hundreds of agents and tools.
- Action: Implement role-based access control (RBAC) for MCP servers, where each agent role is assigned specific permissions dynamically.
Data Provenance Granularity
- The current provenance tracker operates at the level of entire tool outputs. For better security, consider tracking provenance at a finer granularity (e.g., individual fields within a JSON response).
- Action: Use structured metadata to tag individual fields with their provenance.
Runtime Monitoring
- The blog post mentions monitoring unusual tool call sequences but does not specify how to define "unusual." Consider using anomaly detection algorithms (e.g., Isolation Forest or DBSCAN) to identify deviations from normal behavior.
- Action: Integrate an anomaly detection library into the monitoring pipeline.
OWASP Agentic Top 10 Mapping
- The blog post maps threats to OWASP Agentic Top 10 categories but does not provide a complete mapping. For example, ASI04 (Over-Permissioned Agents) is mentioned but not explicitly mapped.
- Action: Expand the mapping to cover all relevant OWASP Agentic Top 10 categories.

Overall Assessment

The blog post is a valuable addition to the repository and provides actionable insights into MCP security. However, some critical areas require enhancement to ensure robust defenses against adversarial attacks. Addressing the flagged issues will significantly improve the security posture of MCP-connected agents.

Suggested Next Steps

Address the 🔴 CRITICAL issues immediately, especially around sanitization, provenance tracking, and webhook security.
Plan for incremental rollout of 🟡 WARNING changes to avoid breaking existing deployments.
Implement 💡 SUGGESTIONS to enhance the usability and scalability of the proposed defenses.

Once these changes are made, the blog post will serve as an authoritative resource for MCP security best practices.

Fix broken relative links in blog post (wrong directory depth), add code/username terms to cspell dictionary, and exclude stackoverflow.com from lychee (returns 404 to automated crawlers). Co-Authored-By: Claude Opus 4.6 <[email protected]>

github-actions

🤖 AI Agent: code-reviewer

Review Summary

This blog post provides an in-depth analysis of the security challenges associated with the Model Context Protocol (MCP) and outlines practical defenses to mitigate risks. The post is well-written, technically accurate, and aligns with the repository's focus on agent governance and security. It also maps the described threats to the OWASP Agentic Top 10, which is highly relevant for the audience of this repository.

However, there are a few areas that could benefit from clarification, additional detail, or minor adjustments to improve the overall quality and accuracy of the post.

🔴 CRITICAL

Tool Poisoning via Description Injection:
- The blog post correctly identifies the risk of hidden instructions in tool descriptions but does not address the possibility of adversaries using obfuscated language or indirect references that evade regex-based detection. For example, adversaries could use synonyms or paraphrasing to avoid detection by simple keyword-based checks.
- Actionable Recommendation: Enhance the sanitization pipeline with an NLP-based classifier trained to detect suspicious patterns and semantic intent in tool descriptions. This could be implemented using pre-trained models fine-tuned for prompt injection detection.
Cross-Server Data Leakage:
- The proposed ProvenanceTracker implementation relies on exact string matching using SHA-256 hashes, which may fail to detect partial matches or modified data. This could allow attackers to bypass provenance checks by slightly altering the data.
- Actionable Recommendation: Replace exact-match SHA-256 with content fingerprinting techniques like MinHash or rolling hashes to detect partial matches and approximate similarity.
Over-Permissioned Tools:
- The blog post highlights the lack of scoping in MCP but does not address the risk of sandbox escape vectors. For example, an attacker could exploit over-permissioned tools to execute arbitrary code or access sensitive files.
- Actionable Recommendation: Implement runtime sandboxing for tools that interact with the filesystem or execute code. Use containerization (e.g., Docker) or syscall filtering (e.g., seccomp) to enforce strict boundaries.

🟡 WARNING

Backward Compatibility:
- The proposed defenses, such as tool allowlisting and fingerprinting, introduce runtime checks that could block previously approved tools if their definitions change. This may break existing deployments without clear migration paths.
- Actionable Recommendation: Provide a backward compatibility mode or a migration guide for organizations adopting these defenses. For example, allow tools to operate in "legacy mode" with warnings instead of immediate blocking.

💡 SUGGESTIONS

Telemetry Implementation:
- The OpenTelemetry-based monitoring setup is a strong recommendation, but the example code could be expanded to include error handling and retries for trace exports.
- Actionable Recommendation: Add retry logic and exception handling to the OTLPSpanExporter setup to ensure resilience in case of network issues.
Human-in-the-Loop Approval:
- The webhook-based approval mechanism is practical but assumes that human operators are always available within the timeout period. This could lead to operational bottlenecks.
- Actionable Recommendation: Implement fallback mechanisms for time-sensitive operations, such as escalating approval requests to a secondary channel or using pre-approved policies for specific scenarios.
Tool Description Sanitization:
- The regex-based sanitization pipeline is a good starting point, but it could benefit from additional checks for overly permissive schemas (e.g., tools that accept arbitrary JSON objects as parameters).
- Actionable Recommendation: Extend the sanitization pipeline to flag schemas with wildcard types or overly generic parameter definitions.
Blog Formatting:
- The blog post is lengthy and dense, which may overwhelm readers. Breaking it into sections with collapsible headers or a table of contents could improve readability.
- Actionable Recommendation: Add a table of contents at the beginning and use collapsible sections for detailed technical content.
Resources Section:
- The resources section mentions the MCP Trust Guide and MCP Security Scanner but does not provide direct links to these resources.
- Actionable Recommendation: Include clickable hyperlinks to the mentioned resources for easier navigation.

Final Thoughts

This blog post is a valuable addition to the repository, offering actionable insights into MCP security. Addressing the flagged critical issues will significantly enhance its accuracy and effectiveness. Additionally, implementing the suggestions will improve usability and readability for the target audience.

aymenhmaidiwastaken · 2026-04-11T23:07:41Z

@imran-siddique CI fixes pushed in 51f7ca9:

Spell check — fixed (added code terms and usernames to .cspell-repo-terms.txt)
Blog post links — fixed (relative paths had wrong directory depth, causing packages/packages/... and a missing file resolution)

Remaining failing checks are on the maintainer side:

test-policies (required) — waiting for status to be reported
Maintainer approval gate — needs fork workflow approval in the Actions tab
link-check (not required) — pre-existing broken SO link in COMMUNITY.md (stackoverflow.com/questions/tagged/agent-governance-toolkit returns 404). I added an exclusion to .lychee.toml but the markdown-link-check workflow doesn't seem to pick up the config. Happy to fix differently if you prefer.

Auto-merge is enabled and your approval is in — should be ready to go once the above are handled.

…1017) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]>

* feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]>

…#1166) * feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs #1017 and #1020 (#1125) PRs #1017 and #1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR #1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR #1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (#1044) Addresses the #1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

…) + critic gap docs (#1170) * feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs #1017 and #1020 (#1125) PRs #1017 and #1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR #1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR #1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (#1044) Addresses the #1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> * docs: address external critic gaps in limitations and threat model (#11) Add three new sections to LIMITATIONS.md addressing gaps identified in public criticism and external security analysis: - §10 Physical AI and Embodied Agent Governance: documents that AGT governs software agents not physical actuators, with mitigations - §11 Streaming Data and Real-Time Assurance: documents that AGT evaluates per-action not continuously over data streams - §12 DID Method Inconsistency Across SDKs: documents the did:mesh vs did:agentmesh split with migration plan for v4.0 Update THREAT_MODEL.md residual risks to reference all three new limitation sections. Co-authored-by: Copilot <[email protected]> * fix!: standardize DID method to did:agentmesh across all SDKs (#12) * fix!: standardize DID method to did:agentmesh across all SDKs BREAKING CHANGE: All agent DIDs now use the did:agentmesh: prefix. The legacy did:mesh: prefix used by Python and .NET has been migrated to match the did:agentmesh: convention already used by TypeScript, Rust, and Go SDKs. Changes: - Python: agent_id.py, delegation.py, entra.py, all integrations - .NET: AgentIdentity.cs, Jwk.cs, GovernanceKernel.cs, all tests - Docs: README, tutorials, identity docs, FAQ, compliance docs - Tests: all test fixtures updated across Python, .NET, TS, VSCode - Version bump: 3.1.0 → 3.2.0 (.NET, Python agent-mesh, TypeScript) Migration: replace did:mesh: with did:agentmesh: in your policies, identity registries, and agent configurations. Co-authored-by: Copilot <[email protected]> * docs: add Q11-Q13 to FAQ — AGT scope, Agent 365, and DLP comparison Adds three new customer Q&As: - Q11: Is AGT for Foundry agents or any agent type? (any) - Q12: Relationship between AGT and Agent 365 (different layers) - Q13: How is AGT different from DLP/communication compliance (content vs action governance) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

…1192) * feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs #1017 and #1020 (#1125) PRs #1017 and #1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR #1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR #1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (#1044) Addresses the #1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> * docs: address external critic gaps in limitations and threat model (#11) Add three new sections to LIMITATIONS.md addressing gaps identified in public criticism and external security analysis: - §10 Physical AI and Embodied Agent Governance: documents that AGT governs software agents not physical actuators, with mitigations - §11 Streaming Data and Real-Time Assurance: documents that AGT evaluates per-action not continuously over data streams - §12 DID Method Inconsistency Across SDKs: documents the did:mesh vs did:agentmesh split with migration plan for v4.0 Update THREAT_MODEL.md residual risks to reference all three new limitation sections. Co-authored-by: Copilot <[email protected]> * fix!: standardize DID method to did:agentmesh across all SDKs (#12) * fix!: standardize DID method to did:agentmesh across all SDKs BREAKING CHANGE: All agent DIDs now use the did:agentmesh: prefix. The legacy did:mesh: prefix used by Python and .NET has been migrated to match the did:agentmesh: convention already used by TypeScript, Rust, and Go SDKs. Changes: - Python: agent_id.py, delegation.py, entra.py, all integrations - .NET: AgentIdentity.cs, Jwk.cs, GovernanceKernel.cs, all tests - Docs: README, tutorials, identity docs, FAQ, compliance docs - Tests: all test fixtures updated across Python, .NET, TS, VSCode - Version bump: 3.1.0 → 3.2.0 (.NET, Python agent-mesh, TypeScript) Migration: replace did:mesh: with did:agentmesh: in your policies, identity registries, and agent configurations. Co-authored-by: Copilot <[email protected]> * docs: add Q11-Q13 to FAQ — AGT scope, Agent 365, and DLP comparison Adds three new customer Q&As: - Q11: Is AGT for Foundry agents or any agent type? (any) - Q12: Relationship between AGT and Agent 365 (different layers) - Q13: How is AGT different from DLP/communication compliance (content vs action governance) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): fix lint errors and remove pi-mono breaking dep scan Two CI failures on main: 1. lint (agent-compliance): W293/W292 trailing whitespace and missing newlines in agt.py and verify.py — fixed. 2. dependency-scan: pi-mono-agentmesh references unregistered npm packages — removed entire pi-mono integration that was merged from draft PR #970 without proper review. Co-authored-by: Copilot <[email protected]> * feat: add AgentMesh component container images and GHCR publishing Add FastAPI server entrypoints for all four AgentMesh components: - trust-engine (port 8443): Agent identity verification, IATP handshakes - policy-server (port 8444): Governance policy evaluation from YAML/JSON - audit-collector (port 8445): Merkle-chained audit logging with persistence - api-gateway (port 8446): Reverse proxy with per-agent rate limiting Infrastructure: - Single Dockerfile with COMPONENT build arg (non-root, tini, health checks) - GitHub Actions workflow for GHCR publishing (multi-arch amd64/arm64) - Helm chart updated to reference ghcr.io/microsoft/agentmesh/* images - 28 integration tests covering all server endpoints Resolves the missing container images that blocked full AgentMesh cluster deployment (images were referenced in Helm chart but never built). Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

* feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs #1017 and #1020 (#1125) PRs #1017 and #1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR #1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR #1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (#1044) Addresses the #1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> * docs: address external critic gaps in limitations and threat model (#11) Add three new sections to LIMITATIONS.md addressing gaps identified in public criticism and external security analysis: - §10 Physical AI and Embodied Agent Governance: documents that AGT governs software agents not physical actuators, with mitigations - §11 Streaming Data and Real-Time Assurance: documents that AGT evaluates per-action not continuously over data streams - §12 DID Method Inconsistency Across SDKs: documents the did:mesh vs did:agentmesh split with migration plan for v4.0 Update THREAT_MODEL.md residual risks to reference all three new limitation sections. Co-authored-by: Copilot <[email protected]> * fix!: standardize DID method to did:agentmesh across all SDKs (#12) * fix!: standardize DID method to did:agentmesh across all SDKs BREAKING CHANGE: All agent DIDs now use the did:agentmesh: prefix. The legacy did:mesh: prefix used by Python and .NET has been migrated to match the did:agentmesh: convention already used by TypeScript, Rust, and Go SDKs. Changes: - Python: agent_id.py, delegation.py, entra.py, all integrations - .NET: AgentIdentity.cs, Jwk.cs, GovernanceKernel.cs, all tests - Docs: README, tutorials, identity docs, FAQ, compliance docs - Tests: all test fixtures updated across Python, .NET, TS, VSCode - Version bump: 3.1.0 → 3.2.0 (.NET, Python agent-mesh, TypeScript) Migration: replace did:mesh: with did:agentmesh: in your policies, identity registries, and agent configurations. Co-authored-by: Copilot <[email protected]> * docs: add Q11-Q13 to FAQ — AGT scope, Agent 365, and DLP comparison Adds three new customer Q&As: - Q11: Is AGT for Foundry agents or any agent type? (any) - Q12: Relationship between AGT and Agent 365 (different layers) - Q13: How is AGT different from DLP/communication compliance (content vs action governance) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(security): address all 14 open code scanning alerts (#13) * fix: address 6 Dependabot security vulnerabilities - python-multipart 0.0.22 → 0.0.26 (DoS via large preamble/epilogue) - pytest 8.4.1 → 9.0.3 (tmpdir handling vulnerability) - langchain-core 1.2.11 → 1.2.28 (SSRF, path traversal, f-string validation) - langchain-core >=0.2.0,<1.0 → >=1.2.28 in langchain-agentmesh pyproject.toml - tsup 8.0.0 → 8.5.1 (DOM clobbering vulnerability) - rand 0.8.5: dismissed #176 as inaccurate (vuln affects rand::rng() 0.9.x API only) Fixes Dependabot alerts: #177, #175, #166, #164, #157, #156 Dismissed: #176 (not applicable to rand 0.8.x) Co-authored-by: Copilot <[email protected]> * fix(security): address all 14 open code scanning alerts Scorecard HIGH: - publish-containers.yml: scope packages:write to job level (#316) Scorecard MEDIUM (pinned dependencies): - docs.yml: pin 4 GitHub Actions by SHA hash (#311-314) - docs.yml: use requirements.txt for pip install (#315) - agent-mesh Dockerfile: pin python:3.11-slim by SHA (#317,#318) - agent-os Dockerfile.sidecar: pin python:3.14-slim by SHA (#295,#296) - dashboard Dockerfile: pin python:3.12-slim by SHA (#291,#293) CodeQL: - test_time_decay.py: timedelta(days=365) -> 366 for leap safety (#289,#290) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

…crosoft#899) Co-authored-by: aymenhmaidiwastaken <[email protected]>

…icrosoft#1017) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#7) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (microsoft#8) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (microsoft#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (microsoft#950) Reflects new capabilities added in PRs microsoft#947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (microsoft#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (microsoft#954) Closes microsoft#952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (microsoft#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (microsoft#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (microsoft#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (microsoft#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (microsoft#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (microsoft#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from microsoft#772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (microsoft#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (microsoft#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (microsoft#908) 15 curated ATR detection rules + sync script. Closes microsoft#901. * fix(docs): correct npm package name and stale version refs across 21 files (microsoft#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (microsoft#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (microsoft#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (microsoft#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (microsoft#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (microsoft#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (microsoft#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]>

* feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#7) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (microsoft#8) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (microsoft#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (microsoft#950) Reflects new capabilities added in PRs microsoft#947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (microsoft#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (microsoft#954) Closes microsoft#952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (microsoft#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (microsoft#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (microsoft#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (microsoft#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (microsoft#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (microsoft#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from microsoft#772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (microsoft#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (microsoft#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (microsoft#908) 15 curated ATR detection rules + sync script. Closes microsoft#901. * fix(docs): correct npm package name and stale version refs across 21 files (microsoft#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (microsoft#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (microsoft#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (microsoft#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (microsoft#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (microsoft#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (microsoft#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]>

…microsoft#1166) * feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (microsoft#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (microsoft#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs microsoft#1017 and microsoft#1020 (microsoft#1125) PRs microsoft#1017 and microsoft#1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR microsoft#1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR microsoft#1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (microsoft#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (microsoft#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#7) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (microsoft#8) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (microsoft#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (microsoft#950) Reflects new capabilities added in PRs microsoft#947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (microsoft#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (microsoft#954) Closes microsoft#952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (microsoft#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (microsoft#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (microsoft#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (microsoft#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (microsoft#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (microsoft#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from microsoft#772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (microsoft#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (microsoft#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (microsoft#908) 15 curated ATR detection rules + sync script. Closes microsoft#901. * fix(docs): correct npm package name and stale version refs across 21 files (microsoft#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (microsoft#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (microsoft#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (microsoft#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (microsoft#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (microsoft#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (microsoft#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (microsoft#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (microsoft#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (microsoft#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (microsoft#1044) Addresses the microsoft#1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (microsoft#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (microsoft#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (microsoft#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (microsoft#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (microsoft#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (microsoft#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (microsoft#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (microsoft#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

…) + critic gap docs (microsoft#1170) * feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (microsoft#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (microsoft#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs microsoft#1017 and microsoft#1020 (microsoft#1125) PRs microsoft#1017 and microsoft#1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR microsoft#1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR microsoft#1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (microsoft#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (microsoft#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#7) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (microsoft#8) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (microsoft#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (microsoft#950) Reflects new capabilities added in PRs microsoft#947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (microsoft#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (microsoft#954) Closes microsoft#952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (microsoft#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (microsoft#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (microsoft#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (microsoft#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (microsoft#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (microsoft#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from microsoft#772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (microsoft#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (microsoft#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (microsoft#908) 15 curated ATR detection rules + sync script. Closes microsoft#901. * fix(docs): correct npm package name and stale version refs across 21 files (microsoft#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (microsoft#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (microsoft#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (microsoft#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (microsoft#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (microsoft#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (microsoft#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (microsoft#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (microsoft#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (microsoft#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (microsoft#1044) Addresses the microsoft#1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (microsoft#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (microsoft#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (microsoft#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (microsoft#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (microsoft#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (microsoft#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (microsoft#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (microsoft#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> * docs: address external critic gaps in limitations and threat model (microsoft#11) Add three new sections to LIMITATIONS.md addressing gaps identified in public criticism and external security analysis: - §10 Physical AI and Embodied Agent Governance: documents that AGT governs software agents not physical actuators, with mitigations - §11 Streaming Data and Real-Time Assurance: documents that AGT evaluates per-action not continuously over data streams - §12 DID Method Inconsistency Across SDKs: documents the did:mesh vs did:agentmesh split with migration plan for v4.0 Update THREAT_MODEL.md residual risks to reference all three new limitation sections. Co-authored-by: Copilot <[email protected]> * fix!: standardize DID method to did:agentmesh across all SDKs (microsoft#12) * fix!: standardize DID method to did:agentmesh across all SDKs BREAKING CHANGE: All agent DIDs now use the did:agentmesh: prefix. The legacy did:mesh: prefix used by Python and .NET has been migrated to match the did:agentmesh: convention already used by TypeScript, Rust, and Go SDKs. Changes: - Python: agent_id.py, delegation.py, entra.py, all integrations - .NET: AgentIdentity.cs, Jwk.cs, GovernanceKernel.cs, all tests - Docs: README, tutorials, identity docs, FAQ, compliance docs - Tests: all test fixtures updated across Python, .NET, TS, VSCode - Version bump: 3.1.0 → 3.2.0 (.NET, Python agent-mesh, TypeScript) Migration: replace did:mesh: with did:agentmesh: in your policies, identity registries, and agent configurations. Co-authored-by: Copilot <[email protected]> * docs: add Q11-Q13 to FAQ — AGT scope, Agent 365, and DLP comparison Adds three new customer Q&As: - Q11: Is AGT for Foundry agents or any agent type? (any) - Q12: Relationship between AGT and Agent 365 (different layers) - Q13: How is AGT different from DLP/communication compliance (content vs action governance) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

…icrosoft#1192) * feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (microsoft#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (microsoft#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs microsoft#1017 and microsoft#1020 (microsoft#1125) PRs microsoft#1017 and microsoft#1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR microsoft#1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR microsoft#1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (microsoft#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (microsoft#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#7) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (microsoft#8) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (microsoft#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (microsoft#950) Reflects new capabilities added in PRs microsoft#947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (microsoft#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (microsoft#954) Closes microsoft#952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (microsoft#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (microsoft#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (microsoft#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (microsoft#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (microsoft#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (microsoft#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from microsoft#772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (microsoft#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (microsoft#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (microsoft#908) 15 curated ATR detection rules + sync script. Closes microsoft#901. * fix(docs): correct npm package name and stale version refs across 21 files (microsoft#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (microsoft#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (microsoft#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (microsoft#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (microsoft#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (microsoft#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (microsoft#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (microsoft#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (microsoft#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (microsoft#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (microsoft#1044) Addresses the microsoft#1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (microsoft#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (microsoft#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (microsoft#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (microsoft#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (microsoft#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (microsoft#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (microsoft#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (microsoft#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> * docs: address external critic gaps in limitations and threat model (microsoft#11) Add three new sections to LIMITATIONS.md addressing gaps identified in public criticism and external security analysis: - §10 Physical AI and Embodied Agent Governance: documents that AGT governs software agents not physical actuators, with mitigations - §11 Streaming Data and Real-Time Assurance: documents that AGT evaluates per-action not continuously over data streams - §12 DID Method Inconsistency Across SDKs: documents the did:mesh vs did:agentmesh split with migration plan for v4.0 Update THREAT_MODEL.md residual risks to reference all three new limitation sections. Co-authored-by: Copilot <[email protected]> * fix!: standardize DID method to did:agentmesh across all SDKs (microsoft#12) * fix!: standardize DID method to did:agentmesh across all SDKs BREAKING CHANGE: All agent DIDs now use the did:agentmesh: prefix. The legacy did:mesh: prefix used by Python and .NET has been migrated to match the did:agentmesh: convention already used by TypeScript, Rust, and Go SDKs. Changes: - Python: agent_id.py, delegation.py, entra.py, all integrations - .NET: AgentIdentity.cs, Jwk.cs, GovernanceKernel.cs, all tests - Docs: README, tutorials, identity docs, FAQ, compliance docs - Tests: all test fixtures updated across Python, .NET, TS, VSCode - Version bump: 3.1.0 → 3.2.0 (.NET, Python agent-mesh, TypeScript) Migration: replace did:mesh: with did:agentmesh: in your policies, identity registries, and agent configurations. Co-authored-by: Copilot <[email protected]> * docs: add Q11-Q13 to FAQ — AGT scope, Agent 365, and DLP comparison Adds three new customer Q&As: - Q11: Is AGT for Foundry agents or any agent type? (any) - Q12: Relationship between AGT and Agent 365 (different layers) - Q13: How is AGT different from DLP/communication compliance (content vs action governance) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): fix lint errors and remove pi-mono breaking dep scan Two CI failures on main: 1. lint (agent-compliance): W293/W292 trailing whitespace and missing newlines in agt.py and verify.py — fixed. 2. dependency-scan: pi-mono-agentmesh references unregistered npm packages — removed entire pi-mono integration that was merged from draft PR microsoft#970 without proper review. Co-authored-by: Copilot <[email protected]> * feat: add AgentMesh component container images and GHCR publishing Add FastAPI server entrypoints for all four AgentMesh components: - trust-engine (port 8443): Agent identity verification, IATP handshakes - policy-server (port 8444): Governance policy evaluation from YAML/JSON - audit-collector (port 8445): Merkle-chained audit logging with persistence - api-gateway (port 8446): Reverse proxy with per-agent rate limiting Infrastructure: - Single Dockerfile with COMPONENT build arg (non-root, tini, health checks) - GitHub Actions workflow for GHCR publishing (multi-arch amd64/arm64) - Helm chart updated to reference ghcr.io/microsoft/agentmesh/* images - 28 integration tests covering all server endpoints Resolves the missing container images that blocked full AgentMesh cluster deployment (images were referenced in Helm chart but never built). Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

* feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (microsoft#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (microsoft#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs microsoft#1017 and microsoft#1020 (microsoft#1125) PRs microsoft#1017 and microsoft#1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR microsoft#1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR microsoft#1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (microsoft#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (microsoft#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#7) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (microsoft#8) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (microsoft#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (microsoft#950) Reflects new capabilities added in PRs microsoft#947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (microsoft#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (microsoft#954) Closes microsoft#952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (microsoft#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (microsoft#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (microsoft#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (microsoft#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (microsoft#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (microsoft#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from microsoft#772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (microsoft#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (microsoft#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (microsoft#908) 15 curated ATR detection rules + sync script. Closes microsoft#901. * fix(docs): correct npm package name and stale version refs across 21 files (microsoft#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (microsoft#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (microsoft#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (microsoft#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (microsoft#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (microsoft#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (microsoft#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (microsoft#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (microsoft#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (microsoft#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (microsoft#1044) Addresses the microsoft#1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (microsoft#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (microsoft#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (microsoft#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (microsoft#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (microsoft#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (microsoft#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (microsoft#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (microsoft#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> * docs: address external critic gaps in limitations and threat model (microsoft#11) Add three new sections to LIMITATIONS.md addressing gaps identified in public criticism and external security analysis: - §10 Physical AI and Embodied Agent Governance: documents that AGT governs software agents not physical actuators, with mitigations - §11 Streaming Data and Real-Time Assurance: documents that AGT evaluates per-action not continuously over data streams - §12 DID Method Inconsistency Across SDKs: documents the did:mesh vs did:agentmesh split with migration plan for v4.0 Update THREAT_MODEL.md residual risks to reference all three new limitation sections. Co-authored-by: Copilot <[email protected]> * fix!: standardize DID method to did:agentmesh across all SDKs (microsoft#12) * fix!: standardize DID method to did:agentmesh across all SDKs BREAKING CHANGE: All agent DIDs now use the did:agentmesh: prefix. The legacy did:mesh: prefix used by Python and .NET has been migrated to match the did:agentmesh: convention already used by TypeScript, Rust, and Go SDKs. Changes: - Python: agent_id.py, delegation.py, entra.py, all integrations - .NET: AgentIdentity.cs, Jwk.cs, GovernanceKernel.cs, all tests - Docs: README, tutorials, identity docs, FAQ, compliance docs - Tests: all test fixtures updated across Python, .NET, TS, VSCode - Version bump: 3.1.0 → 3.2.0 (.NET, Python agent-mesh, TypeScript) Migration: replace did:mesh: with did:agentmesh: in your policies, identity registries, and agent configurations. Co-authored-by: Copilot <[email protected]> * docs: add Q11-Q13 to FAQ — AGT scope, Agent 365, and DLP comparison Adds three new customer Q&As: - Q11: Is AGT for Foundry agents or any agent type? (any) - Q12: Relationship between AGT and Agent 365 (different layers) - Q13: How is AGT different from DLP/communication compliance (content vs action governance) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(security): address all 14 open code scanning alerts (microsoft#13) * fix: address 6 Dependabot security vulnerabilities - python-multipart 0.0.22 → 0.0.26 (DoS via large preamble/epilogue) - pytest 8.4.1 → 9.0.3 (tmpdir handling vulnerability) - langchain-core 1.2.11 → 1.2.28 (SSRF, path traversal, f-string validation) - langchain-core >=0.2.0,<1.0 → >=1.2.28 in langchain-agentmesh pyproject.toml - tsup 8.0.0 → 8.5.1 (DOM clobbering vulnerability) - rand 0.8.5: dismissed microsoft#176 as inaccurate (vuln affects rand::rng() 0.9.x API only) Fixes Dependabot alerts: microsoft#177, microsoft#175, microsoft#166, microsoft#164, microsoft#157, microsoft#156 Dismissed: microsoft#176 (not applicable to rand 0.8.x) Co-authored-by: Copilot <[email protected]> * fix(security): address all 14 open code scanning alerts Scorecard HIGH: - publish-containers.yml: scope packages:write to job level (microsoft#316) Scorecard MEDIUM (pinned dependencies): - docs.yml: pin 4 GitHub Actions by SHA hash (microsoft#311-314) - docs.yml: use requirements.txt for pip install (microsoft#315) - agent-mesh Dockerfile: pin python:3.11-slim by SHA (microsoft#317,microsoft#318) - agent-os Dockerfile.sidecar: pin python:3.14-slim by SHA (microsoft#295,microsoft#296) - dashboard Dockerfile: pin python:3.12-slim by SHA (microsoft#291,microsoft#293) CodeQL: - test_time_decay.py: timedelta(days=365) -> 366 for leap safety (microsoft#289,microsoft#290) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

github-actions Bot added the documentation Improvements or additions to documentation label Apr 7, 2026

github-actions Bot added agent-mesh agent-mesh package size/M Medium PR (< 200 lines) labels Apr 7, 2026

github-actions Bot reviewed Apr 7, 2026

View reviewed changes

imran-siddique requested changes Apr 8, 2026

View reviewed changes

github-actions Bot added the size/L Large PR (< 500 lines) label Apr 8, 2026

github-actions Bot reviewed Apr 8, 2026

View reviewed changes

imran-siddique previously approved these changes Apr 8, 2026

View reviewed changes

aymenhmaidiwastaken dismissed imran-siddique’s stale review via 45d97f4 April 8, 2026 23:45

aymenhmaidiwastaken force-pushed the blog/mcp-security-firewall branch from 7862abd to 45d97f4 Compare April 8, 2026 23:45

github-actions Bot reviewed Apr 8, 2026

View reviewed changes

imran-siddique enabled auto-merge (squash) April 8, 2026 23:50

imran-siddique previously approved these changes Apr 8, 2026

View reviewed changes

aymenhmaidiwastaken and others added 2 commits April 11, 2026 19:01

docs: incorporate reviewer feedback into MCP security blog

fd75d6e

Co-Authored-By: Claude Opus 4.6 <[email protected]>

auto-merge was automatically disabled April 11, 2026 18:01
Head branch was pushed to by a user without write access

aymenhmaidiwastaken dismissed imran-siddique’s stale review via fd75d6e April 11, 2026 18:01

aymenhmaidiwastaken force-pushed the blog/mcp-security-firewall branch from 45d97f4 to fd75d6e Compare April 11, 2026 18:01

github-actions Bot reviewed Apr 11, 2026

View reviewed changes

imran-siddique enabled auto-merge (squash) April 11, 2026 19:11

auto-merge was automatically disabled April 11, 2026 19:21
Head branch was pushed to by a user without write access

github-actions Bot reviewed Apr 11, 2026

View reviewed changes

imran-siddique enabled auto-merge (squash) April 11, 2026 21:48

imran-siddique approved these changes Apr 11, 2026

View reviewed changes

imran-siddique merged commit c58af47 into microsoft:main Apr 13, 2026
75 of 77 checks passed

imran-siddique mentioned this pull request Apr 13, 2026

[v3.1.0] Release showcase — what's new and what's next #931

Closed

MohammadHaroonAbuomar pushed a commit to MohammadHaroonAbuomar/agt-acs that referenced this pull request Jun 1, 2026

blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (mi…

3203613

…crosoft#899) Co-authored-by: aymenhmaidiwastaken <[email protected]>

Conversation

aymenhmaidiwastaken commented Apr 7, 2026

Uh oh!

github-actions Bot commented Apr 7, 2026

Uh oh!

github-actions Bot commented Apr 7, 2026

🌟 What You Did Well

🛠 Suggestions for Improvement

1. File Placement

2. Linting

3. Commit Message

4. Security-Sensitive Content

5. Cross-Referencing Internal Resources

🔗 Helpful Resources

✅ Next Steps

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

🤖 AI Agent: code-reviewer

Feedback on Pull Request: blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall

🔴 CRITICAL

🟡 WARNING

💡 SUGGESTIONS

General Observations

Final Recommendation

Uh oh!

github-actions Bot commented Apr 7, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Security Review of PR: "MCP Security — Why Your AI Agent Tool Calls Need a Firewall"

1. Prompt Injection Defense Bypass

2. Policy Engine Circumvention

3. Trust Chain Weaknesses

4. Credential Exposure

5. Sandbox Escape

6. Deserialization Attacks

7. Race Conditions

8. Supply Chain

Additional Observations:

Summary of Findings:

Recommendations:

Uh oh!

imran-siddique left a comment

Choose a reason for hiding this comment

Uh oh!

aymenhmaidiwastaken commented Apr 8, 2026

Uh oh!

aymenhmaidiwastaken commented Apr 8, 2026

Uh oh!

imran-siddique commented Apr 8, 2026

Uh oh!

aymenhmaidiwastaken commented Apr 8, 2026

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

🤖 AI Agent: code-reviewer

Review Feedback for Pull Request: MCP Security Blog Post

🔴 CRITICAL: Security Concerns

🟡 WARNING: Potential Breaking Changes

💡 SUGGESTIONS: Improvements

Summary

Recommendations

Uh oh!

aymenhmaidiwastaken commented Apr 8, 2026

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

🤖 AI Agent: code-reviewer

Review Summary

🔴 CRITICAL: Security Issues

🟡 WARNING: Potential Breaking Changes

💡 Suggestions for Improvement

Final Recommendation

Uh oh!

imran-siddique commented Apr 8, 2026

Uh oh!

imran-siddique left a comment

Choose a reason for hiding this comment

Uh oh!

aymenhmaidiwastaken commented Apr 8, 2026

Uh oh!

github-actions Bot commented Apr 7, 2026 •

edited

Loading