rdc-endpoint-setup

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

• Third-party content exposure detected (high risk: 0.70). This skill wraps async functions that fetch data from third-party services (e.g., Firebase/Firestore examples, Supabase queries, and WebSocket message handlers) so the agent would ingest and process untrusted/user-generated content from those external sources at runtime.