proxyman-traffic-debugging

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow uses Proxyman MCP to inspect and export captured flows and WebSocket messages from a locally running Proxyman instance (including potential outsider-authored network traffic), but it does not describe any direct ingestion of outsider-authored free text from a user-postable queue/feed or monitored community/comment source.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill instructs the agent to perform system-changing operations (install/uninstall certificates, enable/modify system proxy, inject terminals/electron, run guided automations) that can require elevated privileges or alter host security, so it can compromise the machine state.