oxidized-agentic-audit
Version updated for https://github.com/jbovet/oxidized-agentic-audit to version v0.6.0.
- 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, scripts, and related files for vulnerabilities, such as dangerous patterns, prompt injection risks, and supply chain threats. It automates the detection of issues like unsafe code execution, malicious URLs, PII exposure, and obfuscated content, using language-specific and context-aware rules. This action helps developers proactively identify and mitigate security risks in their AI agent workflows.
What’s Changed
What’s Changed
- fix: ensure PATTERNS and PATTERN_SET synchronization in bash and type… by @jbovet in https://github.com/jbovet/oxidized-agentic-audit/pull/15
- feat: add malicious URL, obfuscation, PII, and script-mixing scanners by @jbovet in https://github.com/jbovet/oxidized-agentic-audit/pull/16
Full Changelog: https://github.com/jbovet/oxidized-agentic-audit/compare/v0.5.0...v0.6.0