oxidized-agentic-audit
Version updated for https://github.com/jbovet/oxidized-agentic-audit to version v0.5.0.
- 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
The oxidized-agentic-audit GitHub Action is a security scanning tool designed to analyze AI agent skills and directories for vulnerabilities such as dangerous code patterns, prompt injection risks, and supply chain threats. It automates tasks like static analysis, secret scanning, and security scoring, providing multi-format output and a suppression system for streamlined auditing. This tool helps developers identify and mitigate security risks in AI-related projects effectively.
Release notes
What’s Changed
- feat: add validation rules for agent and skill names to prevent leading/trailing hyphens and consecutive hyphens by @jbovet in https://github.com/jbovet/oxidized-agentic-audit/pull/12
- refactor: rename audit command replacing by scan by @jbovet in https://github.com/jbovet/oxidized-agentic-audit/pull/13
- test: add unit test for backcompat by @jbovet in https://github.com/jbovet/oxidized-agentic-audit/pull/14
Full Changelog: https://github.com/jbovet/oxidized-agentic-audit/compare/v0.4.0...v0.5.0