Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

GitHub project collects jailbreak prompts for 26+ models

AI summary

The toggg53192-cmd/jailbreaks repository contains 32 system prompts and jailbreak configurations targeting more than 26 frontier, open-weight, and free stealth models. It includes persona definitions, workspace policies, AGENTS.md files, configuration blocks, and Ollama Modelfiles, with maintainers describing each file as complete and paste-ready. The repository also warns that prompt behavior is version-dependent and that users must follow applicable provider terms.

In-depth insight

The collection offers researchers and developers a cross-model reference for studying instruction hierarchies, prompt conflicts, and prompt-injection defenses, although its compatibility and effectiveness claims remain untested.

LIST OF ALL MY JAILBREAKS


Jailbreaks

A curated collection of system prompts, persona locks, workspace policies, and agent operating specifications for frontier, open-weight, and free stealth models.

Prompts
Targets

#OpenCode Zen#GLM#DeepSeek#Kimi#Qwen#Gemma#GPT-OSS#Claude#Gemini#Grok#Mistral#Ollama

Original · 4 min readRead the original
Group chat

No comments yet. Start the conversation.