Pipelock Agent Security Scan
Actively maintainedluckyPipewrench/pipelock · Apache-2.0
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.
★ 786 starsLast commit todayLatest v3.3.0
B
79
/ 100
Security signals
OpenSSF Scorecard9.7 / 10
SECURITY.md presentYes
Immutable releasesNot enabled
Known vulnerabilitiesNone on record
How to use it safely
Recommended: pin to commit SHA
uses: luckyPipewrench/pipelock@de451af38bcd46e1143682fd2200ebf045cf8647 # v3.3.0Mutable tags like v3.3.0 can be rewritten to point at malicious commits. Pinning to the full commit SHA is the only reference GitHub guarantees immutable.
Full workflow example
steps: - uses: luckyPipewrench/pipelock@de451af38bcd46e1143682fd2200ebf045cf8647 # v3.3.0
Score breakdown
Security (35%)88
Popularity (20%)49
Maintenance (30%)100
Reliability (15%)58