Basilisk AI Security Scan

Version updated for https://github.com/regaan/basilisk to version v1.0.8.

• 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 open-source AI red teaming and security testing framework designed to identify vulnerabilities in large language models (LLMs) through automated adversarial prompt testing and genetic prompt evolution. It helps security researchers, penetration testers, and AI safety engineers uncover issues like jailbreaks, data exfiltration risks, and logic bypasses, providing tools for forensic audits and comparative evaluations across different LLMs. The framework streamlines the process of stress-testing AI systems to enhance their security and robustness.

Release notes

🐍 Basilisk v1.0.8

AI Red Teaming Framework — Smart Prompt Evolution for LLM Security Testing.

Downloads

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/regaan/basilisk/compare/.../v1.0.8

• regaan
• GitHub Actions