relay-mutations-patterns

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

• Third-party content exposure detected (high risk: 0.70). The skill includes runtime ingestion and display of user-generated comments (e.g., RealtimeComments.jsx using requestSubscription on commentAdded and CreateComment.jsx/CreateComment component that accepts and inserts arbitrary comment bodies into the store/UI), which are untrusted third-party inputs the agent would read and render.