Fully autonomous AI hacker to find actual exploits in your web apps. Shannon has achieved a 96.15% success rate on the hint-free, source-aware XBOW Benchmark.

Security operations toolkit for AI coding agents. Give Claude Code 25+ skills to catch vulnerabilities, scan containers, detect secrets, and enforce policies automatically.

GhostCrew is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and pentesting workflows.

A GPT-empowered penetration testing tool

CMS Detection and Exploitation suite - Scan WordPress, Joomla, Drupal and over 180 other CMSs

60k+ WordPress Nuclei templates, updated daily from Wordfence intel—filter by severity/tags/CVE and scan in one line. 🚀🔒

Wordpress XMLRPC System Multicall Brute Force Exploit (0day) by 1N3 @ CrowdShield

A Ruby framework designed to aid in the penetration testing of WordPress systems.

渗透测试有关的POC、EXP、脚本、提权、小工具等---About penetration-testing python-script poc getshell csrf xss cms php-getshell domainmod-xss csrf-webshell cobub-razor cve rce sql sql-poc poc-exp bypass oa-getshell cve…

A curated list of awesome LLM Red Teaming training, resources, and tools.

AI Red Teaming playground labs to run AI Red Teaming trainings including infrastructure.

Reference notes for Attacking and Defending Generative AI presentation

Repo containing reports and PoCs for a selection of vulnerabilities I have discovered and that have been assigned a CVE identifier.

A repository for quickly generating trojaned RL models

A repository to quickly generate synthetic data and associated trojaned deep learning models

Adversarial AI - Attacks, Mitigations, and Defense Strategies, published by Packt

Artifacts supporting the paper: “When Secure Isn’t: Assessing the Security of Machine Learning Model Sharing"

A list of backdoor learning resources

Buttercup CRS as submitted to the AIxCC Final Competition

Privacy Testing for Deep Learning

A Python pickling decompiler and static analyzer

Saves Discord chat logs to a file

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we confi…

The framework for AI souls

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.

Autonomous Multi-Agent Based Red Team Testing Service / AI hacker

The most hackable AI agent