Basilisk AI Security Scan
Version updated for https://github.com/noobforanonymous/basilisk to version v1.0.2.
- This action is used across all versions by ? repositories.
Action Type
This is a Composite action.
Go to the GitHub Marketplace to find the latest changes.
Action Summary
Basilisk is an advanced security framework designed for red teaming AI and LLM applications, offering comprehensive OWASP LLM Top 10 attack coverage. It uses a genetic prompt evolution engine to automate the discovery of novel security bypasses, enabling offensive security testing beyond static tools. The action streamlines tasks like model vulnerability assessments, response divergence detection, and guardrail posture scanning, helping teams identify weaknesses and improve AI system defenses efficiently.
Release notes
🐍 Basilisk v1.0.2
AI Red Teaming Framework — Smart Prompt Evolution for LLM Security Testing.
Downloads
| Platform | File |
|---|---|
| Windows | .exe (NSIS installer) |
| macOS | .dmg (Apple Disk Image) |
| Linux (Universal) | .AppImage |
| Arch Linux | .pacman |
| Ubuntu/Debian | .deb |
| Fedora/RHEL | .rpm |
Install via pip
pip install basilisk-ai
Install via Docker
docker pull rothackers/basilisk
docker run --rm rothackers/basilisk scan --help
Full Changelog: https://github.com/noobforanonymous/basilisk/compare/.../v1.0.2