jailbreak

This is The most comprehensive prompt hacking course available, which record our progress on a prompt engineering and prompt hacking course.

Bypass restricted and censored content on AI chat prompts 😈

Red Teaming python-framework for testing chatbots and GenAI systems.

HacxGPT Jailbreak 🚀: Unlock the full potential of top AI models like ChatGPT, LLaMA, and more with the world's most advanced Jailbreak prompts 🔓.

[New Update](Added Agentic-Mode, Dark-GODMode)The Real BlackHat GPT - ai can do your illegal stuffs without saying anything. Use At Your Own Risk!

冷咖啡 ColdBrew 四合一破甲正式版 — GPT-5.6 / Claude / Grok 4.6 / DeepSeek v4 Pro 一键部署 · 启动 · 恢复 · 打包发布 | QQ 群 1057540028 / 1077074552

Ultra-fast, low latency LLM prompt injection/jailbreak detection ⛓️

LLM alignment jailbreak; a set of instructions for auditing their internal reasoning and uncovering biases

Official PyTorch Implementation for the "Recovering the Pre-Fine-Tuning Weights of Generative Models" paper (ICML 2024).

A living map of the AI agent security ecosystem.

A repo for all the jailbreaks

Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models

High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.

[CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

Türkçe yapay zeka güvenliği için açık kaynak çatı: rehber serisi, uygulamalı akademi, araştırma & deneyler, 23+ araç ve 20 Hugging Face veri seti + model.