Trending repositories: red-teaming
7 tracked repositories tagged with red-teaming, ordered by stars. Use the topic filters below to narrow further.
7 of 7 repositories
usestrix/strix
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
AI summary: Open-source AI penetration testing tool that autonomously finds and fixes vulnerabilities.
49,439securityPythonApache-2.0elder-plinius/CL4R1T4S
LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
AI summary: An advanced, experimental AI agent framework focused on complex reasoning and task execution.
46,786ai-mlAGPL-3.0KeygraphHQ/shannon
Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.
AI summary: A high-performance, open-source knowledge graph engine optimized for fast querying and AI integration.
46,488dataTypeScriptAGPL-3.0promptfoo/promptfoo
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
AI summary: A testing and red-teaming framework for evaluating prompts, RAG pipelines, and LLM applications.
24,054developer-toolsTypeScriptMITelder-plinius/G0DM0D3
LIBERATED AI CHAT
AI summary: A multi-model AI testing framework that races various LLMs in parallel using red-teaming techniques and comparative evaluation.
10,230ai-mlTypeScriptAGPL-3.0elder-plinius/OBLITERATUS
OBLITERATE THE CHAINS THAT BIND YOU
AI summary: Advanced toolkit for systematically understanding and removing refusal behaviors from large language models.
7,355ai-mlPythonAGPL-3.0MDX-Tom/gpt-5.6-instruct
A Codex jailbreak prompt and test pack for gpt-5.6-sol. 针对 gpt-5.6 系列的 Codex 破甲提示词与测试包。
AI summary: A comprehensive jailbreak prompt and testing suite specifically targeting the gpt-5.6-sol model.
4,816securityPythonMIT