render-debug

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and analyze user-generated Render logs and database/query results (e.g., list_logs(...), query_render_postgres(...)) in SKILL.md, which are untrusted third-party content the agent will read and use to decide fixes, creating a clear vector for indirect prompt injection.