jailbreak-prompts

LLM Jailbreaks, ChatGPT, Claude, Llama, DAN Prompts, Prompt Leaking

[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!

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

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

This is the public code repository of paper 'JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs' (ACL 2025)

Utterly unelegant prompts for local LLMs, with scary results.

Bootstra AI Jailbreak for iOS: The World’s First AI-Powered Jailbreaking Tool

Данный репозиторий создан для снятия ограничений с ИИ с помощью jailbreak-промптов.

Roblox Jailbreak Script 2026 themed toolkit for heist planning, vehicle tracking, cash progression, routes, loadouts and gameplay analytics.

Grok 场景路由交付合约 · 模型安全研究

A curated archive of 63 prompts for large language models, sorted into eleven categories and kept as plain text so nothing is reformatted on the way out. Includes alignment testing prompts for research.

A tool for auditing bias through large language models

A framework to evaluate how open-source language models handle adversarial prompts. Tests across hallucination traps and jailbreak scenarios.

AI security testing — find security vulnerabilities in LLM apps, chatbots, AI agents, MCP servers, and RAG systems. Mapped to OWASP (LLM, Agentic, MCP) and NIST AI RMF.