Pipelock Agent Security Scan

Version updated for https://github.com/luckyPipewrench/pipelock to version v0.3.6.

  • 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

Pipelock is an open-source agent firewall designed to monitor and secure AI agents by detecting and blocking sensitive data leaks, such as API keys, during HTTP requests. It automates the protection of AI agents by scanning and filtering outgoing network traffic, offering flexible deployment options like forward proxy and fetch proxy modes, with no code changes required. Its key capabilities include data loss prevention (DLP), seamless integration with popular AI agent frameworks, and robust security features like SLSA build provenance and SBOM verification.

Release notes

Changelog

  • 165a7e2d23bd907ab0ef965f664c2414ed2addde feat: add TLS interception for CONNECT tunnel scanning (#183)
  • aa1f60a9d6d949ec34b3376a48a66da527ecdd57 feat: add parameter schema scanning to MCP tool poisoning detection (#179)
  • e78d08a33f72558ec345b2c8b57de4e69ae22431 feat: add pipelock report command for HTML/JSON audit reports (#180)
  • ca1cfbe9a50269921a3f82f4ce8b0e711d3f7bdf fix: skip well-known non-secret env vars in leak detection (#182)