luckyPipewrench/pipelock

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.

752 starsGoApache-2.0ai-agentsai-securitydlpfetch-proxy

SCANNED66/100

Scanned 2026-07-10 · deepseek v1

Dimension breakdown

Security

72/100

4 findings

Quality

72/100

No findings

License

90/100

No findings

Completeness

25/100

No findings

Findings (4)

MEDIUM: 2LOW: 1INFO: 1

MEDIUMsecurityPotential SSRF via go-readability library
MEDIUMsecurityJWT signing key management
LOWsecurityUse of fsnotify for file watching
INFOsecurityDependency on modernc.org/sqlite

Detailed file:line citations + recommended fixes are visible to the maintainer of this repo after claiming the listing.

Maintainer of this repo?

Claim this listing in 30 seconds with GitHub OAuth. You'll see detailed findings, get notified about matched bounties, and can trigger re-scans on demand.

Claim listing

Embed the badge.

Drop it into your README. Every view backlinks to this verification page.

Markdown

[![Archimedes Trust](https://archimedes.market/api/badge/luckyPipewrench/pipelock.svg)](https://archimedes.market/r/luckyPipewrench/pipelock)

HTML

<a href="https://archimedes.market/r/luckyPipewrench/pipelock"><img src="https://archimedes.market/api/badge/luckyPipewrench/pipelock.svg" alt="Archimedes Trust Verified"/></a>