radon-mcp

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

• Third-party content exposure detected (high risk: 0.80). The skill's view_network_logs and view_network_request_details tools explicitly surface HTTP requests and response bodies/headers from the running app (arbitrary external URLs) which are untrusted third‑party content the agent is instructed to read and use for debugging and follow‑up actions.