Pipelock Agent Security Scan
Version updated for https://github.com/luckyPipewrench/pipelock to version v1.2.0.
- 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 secure AI agents by monitoring and controlling their HTTP traffic to prevent accidental data leaks, such as exposing sensitive API keys. It automates the detection and blocking of unauthorized or risky data transmissions, ensuring robust data loss prevention without requiring code changes or additional dependencies. Key features include compatibility with various AI SDKs and frameworks, support for proxy modes, and simple deployment options.
Release notes
Changelog
- b546d9165aa3eaa5f488e9c8a36c5081f3464ae0 feat: add DLP prefix pre-filter to skip regex on clean traffic (#209)
- 8f31933b3d9df121f8392d0ff4779a55ac6a2dc9 feat: cross-request exfiltration detection (CEE) (#206)
- 767f3d01d29ef395302d22caa645cbdfa6558b66 feat: expand DLP patterns from 22 to 36 (#208)
- 6471b7f3f05af7db6783a01f744f3d81be6d2503 fix: normalize license headers, update docs for dual-license clarity (#204)
- d9932237edffd5f5ba67d6980067daa8f1f51dbe fix: shut down agent listeners on config reload when license revoked (#205)