achurch

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to fetch and read public, user-generated content—including lyrics and theological context via achurch.ai endpoints (e.g., /api/music/{slug}/lyrics and /api/music/{slug}/context), transient community reflections returned by /api/attend, and external streams (YouTube/Twitch) and GitHub contributions—so the agent will ingest untrusted third-party content as part of its workflow.