elder-plinius/CL4R1T4S

This page introduces an external open-source repository. It is not an HDATF product.

What it does

A collection of system prompts, guidelines and tool definitions reportedly extracted from major AI models and agents. It is published with the stated aim of making AI systems more transparent.

How it helps ATF

Loosely related. It suggests that system prompts of AI products can be extracted, so it could serve as a reminder that access control in the ATF Works assistant should rest on permission checks, not on prompt text.

License

AGPL-3.0 Network copyleft. Offering a modified version as a service also requires releasing the source. Review before any product use.

More in this category

• soxoj/maigret
  Maigret builds a dossier on a person from a username alone, checking more than 3,000 sites for accounts and gathering the information available on those pages. It needs no API keys.
• Z4nzu/hackingtool
  A Python toolkit that gathers security testing tools by category, such as recon, OSINT, web, wireless and forensics, for authorized testing. An AI layer turns a plain-English request into a matching tool and command.
• HunxByts/GhostTrack
  A Python command-line tool for information gathering. Its menus look up information about an IP address, a phone number or a username on social media.
• google/magika
  Magika identifies a file's content type with a small deep learning model that runs on a single CPU. It was trained on more than 200 binary and text content types and has a command-line tool.
• mukul975/Anthropic-Cybersecurity-Skills
  A community library of cybersecurity skills for AI agents, not affiliated with Anthropic, mapped to frameworks such as MITRE ATT&CK and NIST CSF 2.0. It includes offensive and dual-use techniques for authorized penetration testing, security research, defense and education.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.