github.comrepoAll-AI-Jailbreaks
A GitHub repository archiving 19 jailbreak, prompt-injection, persona-conditioning, and response-format-manipulation prompts collected against DeepSeek, Gemini, GLM, Grok, Kimi, Qwen, Sonnet, and ChatGPT. Prompts are kept close to their original form for provenance/reproducibility, positioned as a corpus for red-teaming and robustness evaluation rather than a guaranteed exploit list, with guidance to test in isolated environments and log model version/config/date/response per trial.
TL;DR A growing GitHub archive of 19 raw jailbreak/prompt-injection prompts across DeepSeek, Gemini, GLM, Grok, Kimi, Qwen, Sonnet, and ChatGPT for LLM red-teaming.
Techniques named here
- Prompt Injection
- Jailbreak prompting
- Persona-conditioning
- Response-format manipulation
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle