Version updated for https://github.com/regaan/basilisk to version v2.0.0.

• This action is used across all versions by 0 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 framework designed for automated security testing of large language models (LLMs) such as GPT, Claude, and custom APIs. It streamlines adversarial testing through features like genetic prompt evolution, posture scanning, behavior comparison across models, and detailed reporting, enabling security researchers and defensive teams to identify vulnerabilities in LLM applications. The framework simplifies repeatable LLM security workflows and enhances model robustness by automating complex testing scenarios.

Release notes

Basilisk v2.0.0

Highlights

• Shared runtime and hardened desktop/backend boundary
• Evidence-backed findings with trust tiers and downgrade policy
• Campaign control plane, retention controls, and stronger audit flow
• Improved SPE-NL evolution, curiosity, probes, and eval workflow
• Native library verification, secret handling hardening, and safer persistence
• New beginner and advanced documentation for CLI and desktop

Notes

• GitHub Actions builds desktop artifacts for Linux, Windows, and macOS
• Community builds may be unsigned depending on platform signing availability
• See the README and docs for full usage and architecture details

• regaan
• GitHub Actions