skillspector

企业级 AI 资源纳管平台，提供统一 AI网关、Token调度能力，纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型，并支持 MCP 工具与 Skill 的集中注册分发。具备内外双轨定价、成本归因、统一身份认证、安全审计与效能报表，帮助企业精准控制成本、量化 ROI，高效治理 AI 资产。

Run NVIDIA SkillSpector in GitHub Actions to scan AI agent SKILL.md repos, upload SARIF, and report PR findings.

🛡️ Streamlit dashboard wrapping NVIDIA SkillSpector CLI — scan AI agent skills, Claude MCP tools & Cursor extensions for prompt injection, data exfiltration & 64 vulnerability patterns. Visual risk score, severity chart & remediation guide.

Autonomous Agent Skill Creator & AST Security Evaluator (Agent Skills Spec 1.0 + NVIDIA SkillSpector). Zero-dependency bundle for Claude Code, Cursor, Antigravity, & Windsurf.

Dependabot for Claude Code Skills: detect upstream drift in installed Skills, re-score risk with SkillSpector, and auto-open GitHub Issues. Supply-chain security monitoring as a GitHub Action + Go CLI.

Security-reviewed skills, rules, and reusable memory for AI agents

Open-source AI skill intake and policy guardrails. Four behavior modes, deterministic decisions, and practical harness guidance by Khaldoon Esmail.

🛡️ Zero-trust security gate & vulnerability scanner for AI agent skills (Claude Code, Antigravity, OpenCode, Codex). Powered by NVIDIA SkillSpector.

Reference example: org-managed Claude Code plugin marketplace with a SkillSpector security gate on every PR

Generate polished PDF reports from NVIDIA SkillSpector scan results

A visual frontend for NVIDIA SkillSpector — making AI agent skills easier to explore and understand.