AndreSzymanski15/ai-jailbreaks
Can I trust it?
Be careful with this one.
Warnings Check
Very new: it was created yesterday. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.
Quick checks from public data. They help, but they are no guarantee.
What it is
Collection of 35 copy-paste prompts (system prompts, persona definitions, AGENTS.md files, Ollama Modelfiles) that aim to alter how 25+ LLMs respond, including refusal behavior. Documented for AI security research and red-team testing.
Who it's for
Security researchers and developers doing red-team testing or prompt-injection hardening of LLMs
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up AndreSzymanski15/ai-jailbreaks in my project. Follow its README: https://github.com/AndreSzymanski15/ai-jailbreaks. Explain each step and check it is safe before running anything.
Star curve
On the radar
Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.
Records
- Best place on RepoAlerts: #12, on 20 Oct 2026
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
18,267 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/AndreSzymanski15/ai-jailbreaks?ref=badge)Similar repos
- whitecircle/rise
A research framework for automated red-teaming of text-to-image models. It evolves natural-language attack strategies with an island-model evolutionary search, scores them with a VLM judge against cat
- aimeoa/hanshuang-codex
Windows desktop app that installs a user-supplied prompt file into the configuration files of several AI coding assistants and deploys a bundled reverse-engineering toolkit. It also includes uninstall
- inwpu/SapperLens
An independent architectural analysis of N1nEmAn's sapper-v2 multi-agent penetration testing system. It reverse-engineers the system's prompts, scheduling loop and concurrency model, and cross-checks
- JoasASantos/REA-Prompts
A curated collection of prompts for using REA (Reverse Engineer Anything) with an AI coding agent to inspect how software works, covering native binaries, firmware, kernels, games, Electron apps, APKs
- ifixai-ai/iFixAi
A Python tool that audits AI agents by running diagnostic inspections to check whether an agent performs the job it is supposed to do, combining adversarial testing with operational assurance. It can
- trhhubsd/ARTEX
Autonomous AI penetration testing system written in Go with a Next.js web UI. It runs LLM-driven agents against targets, records traffic through a proxy, syncs assets from ScopeSentry, and tracks find