Pipelock Agent Security Scan

Version updated for https://github.com/luckyPipewrench/pipelock to version v1.0.0.

  • 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

Pipelock is an open-source agent firewall designed to protect AI agents by monitoring and blocking unauthorized or malicious HTTP requests, such as those attempting to leak sensitive data like API keys. It automates security for AI agents by intercepting their network traffic and scanning it for vulnerabilities or data leaks, operating as a single binary without runtime dependencies. Key features include compatibility with various AI frameworks, support for proxy modes, and seamless integration without requiring code changes.

Release notes

Changelog

  • 9e2bc5bed87502e7bfe80e56bec112fb642ee92f feat: add per-agent identity, budgets, and config isolation (#186)
  • 413f20f0fe5244bf7ddb8510932b8ce4ea25ef7c feat: add persistence detection for MCP tool policy and chain patterns (#187)
  • 11c38f71476e8baaa8207b5d94bf1c7d121c6303 fix: TLS interception follow-up (shared transport, reload warnings, certgen coverage) (#185)