Security Tools
Open-source tools for AI red teaming, security reconnaissance, and offensive research. Built for practitioners.
AI Red Teaming
AATMF Red Teaming Toolkit
Python CLI for systematic LLM safety testing — three-layer evaluation pipeline, defense fingerprinting, regression tracking, attack chain planning. Mapped to the full AATMF taxonomy.
TheJailBreakChef Engine
AATMF-powered adversarial prompt engineering workbench. Transform raw intent into structured, framework-backed prompts using AATMF attack phases, PHLRA context injection, and Cialdini influence principles.
The LLM Red Teamer's Playbook
MarkdownDiagnostic methodology for bypassing LLM defense layers — from input filters to persistent memory exploitation. Mapped to AATMF taxonomy.
Burp MCP Toolkit
PythonMCP security analysis for Burp Suite — test Model Context Protocol servers for prompt injection and tool poisoning.
Claude-Red
MarkdownCurated library of offensive security skills for Claude — red team operations, vulnerability research, and adversarial AI testing.
Reconnaissance & Bounty
JustDASTit
PythonThe Burp You Can Afford — open-source CLI DAST toolkit for web application vulnerability scanning and XSS detection.
SnailHunter
PythonAI-powered bug bounty automation — combines LLM analysis with traditional security scanning for vulnerability discovery.
Xposure
PythonAutonomous credential intelligence platform — discovers, extracts, correlates, and verifies exposed secrets across target attack surfaces.
SnailSploit Recon
JavaScriptChrome MV3 extension for passive reconnaissance and bug bounty recon automation.
Research & PoCs
ChatGPT-DNS-Exfill
ResearchDNS exfiltration via ChatGPT Canvas — rendered content triggers DNS lookups without HTTP requests.
chatgpt-rce-dns
ResearchValidating DNS exfiltration and Python Pickle RCE attack chains in AI code execution sandboxes.
Related Research
Offensive Tools
Infrastructure
All tools are open-source and available on GitHub
Visit GitHub Profile →