claude-peers-mcp

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow facilitates communication between local Claude Code instances via a broker daemon, where messages from other peers are ingested by the agent.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning and installing code from an arbitrary personal GitHub repository (https://github.com/louislva/claude-peers-mcp.git), constituting an unverified third-party runtime dependency.