data-client-endpoint-setup

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

• Third-party content exposure detected (high risk: 0.70). The skill's examples explicitly read data from third-party services and user-generated sources—see the "Firebase/Firestore", "Supabase", and "WebSocket Fetch" sections which fetch documents, query Supabase tables, and receive socket messages—so the agent would ingest and process untrusted external content at runtime.