render-debug

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads Render build/runtime logs via MCP calls like list_logs(...) and then analyzes the returned free-text log message/text, which can contain outsider-authored content (e.g., injected into application logs by external users/inputs) without selecting a specific trusted item first.