Alejandros17487/ai-jailbreaks
AI skill
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 about 35 jailbreak prompts, system prompts and agent configuration files aimed at bypassing safety behavior in various AI models, including Ollama Modelfiles. The README states it is intended for security research and red-team testing.
Who it's for
AI security researchers and red-team testers studying model safety and prompt injection
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 Alejandros17487/ai-jailbreaks in my project. Follow its README: https://github.com/Alejandros17487/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: #32, on 22 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.
18,934 GitHub repos watched and ranked every hour. Figures as of 22 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/Alejandros17487/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
- zero-lab-ai/skills
A collection of 56 portable security skills, grouped into 10 installable plugins, for authorized defensive assessment, penetration testing, red teaming, detection engineering and engagement operations
- JoasASantos/REA-Prompts
A collection of prompts for the REA (Reverse Engineer Anything) toolset, which lets an AI coding agent inspect how software works, covering native binaries, firmware, games, Electron apps, APKs and we
- ZeroDayEvil/ai-security-tool
Desktop and web terminal client with SSH, SFTP, RDP, VNC, serial and other protocols, CVE and SBOM supply chain scanning, and a set of AI agents that automate security workflows. The README also lists
- Passionvonhover/MemX-rpocket-team-Jailed
A repository with HTML code and topics referring to linked lists, red-black trees, string manipulation, queues and an iOS jailbreak context. No description or README is provided, so its purpose cannot
- aimeoa/hanshuang-codex
Windows desktop app built with Electron. It installs a user-supplied prompt file into the instruction files of several AI coding assistants (Codex, Cursor, Claude, OpenCode and others), can restore th