ai-red-teaming

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

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

A security scanner for your LLM agentic workflows

A comprehensive guide to adversarial testing and security evaluation of AI systems, helping organizations identify vulnerabilities before attackers exploit them.

Open-source adversary emulation for AI agents and MCP servers.

A curated list of MLSecOps tools and resources for securing machine learning and AI systems - adversarial ML defense, LLM security, AI red teaming, model scanning, supply-chain protection, and MLOps pipeline security.

A collection of servers which are deliberately vulnerable to learn Pentesting MCP Servers.

This document curates open-source projects, academic papers, capability benchmarks, and commercial solutions (international & China) in AI penetration testing, LLM red teaming, autonomous offensive agents, and vulnerability discovery—aimed at helping researchers, security engineers, and enterprise decision-makers quickly form a holistic view.

Whistleblower is a offensive security tool for testing against system prompt leakage and capability discovery of an AI application exposed through API. Built for AI engineers, security researchers and folks who want to know what's going on inside the LLM-based app they use daily

Open-source adversarial testing engine, SDK, and CLI for AI agents. Runs locally or against the Humanbound Platform.

A sophisticated, automated, AI‑driven cyber‑operations framework designed for state‑level offensive and defensive security research, this project integrates zero‑click exploit deployment, autonomous post‑exploitation, and advanced device‑control capabilities into a unified command‑and‑control architecture.

AspGoat is an intentionally vulnerable ASP.NET Core application for learning and practicing web application security.

Code scanner to check for issues in prompts and LLM calls

Open-source AI security verification — model artifacts, live endpoints, MCP servers and recorded agent traces. One rule engine for your laptop, CI and production, mapped to OWASP/MITRE ATLAS/NIST. Deterministic evidence, a measured verdict, and an explicit "could not tell". Apache-2.0.

A diagnostic methodology for bypassing LLM defense layers — from input filters to persistent memory exploitation.

Open-source LLM Prompt-Injection and Jailbreaking Playground

Awesome LLM security tools, research, and documents

AI security and prompt injection payload toolkit

Basilisk — Open-source AI red teaming framework with genetic prompt evolution. Automated LLM security testing for GPT-4, Claude, Grok, Gemini. OWASP LLM Top 10 coverage. 32 attack modules.

Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI