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.

823Stars on the repository
8Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

clean-skill

01

luckyPipewrench/pipelock

Skill Claude CodeCodex

Reads a local status file and calls a local health endpoint.

823 3d ago A 16 tokens original Apache-2.0

combo-skill

02

luckyPipewrench/pipelock

Skill Claude CodeCodex

Demonstrates a source and sink combination for scanner tests.

823 3d ago A 16 tokens original Apache-2.0

deps-skill

03

luckyPipewrench/pipelock

Skill Claude CodeCodex

Mentions dependency install commands for inventory.

823 3d ago A 12 tokens original Apache-2.0

direct-skill

04

luckyPipewrench/pipelock

Skill Claude CodeCodex

Direct credential transfer on a single command for scanner tests.

823 3d ago A 15 tokens original Apache-2.0

hidden-skill

05

luckyPipewrench/pipelock

Skill Claude CodeCodex

Contains a hidden Unicode control for delegated scan coverage.

823 3d ago A 14 tokens original Apache-2.0

prose-skill

06

luckyPipewrench/pipelock

Skill Claude CodeCodex

Prose mentions that must not produce combination findings.

823 3d ago A 15 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: