shader-extract

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow (Router/Kernel) ingests outsider-authored free text when a user supplies an arbitrary webpage URL (Standalone mode), because the agent navigates to that page and extracts source/runtime/shader evidence from it as part of capture (surface lock → source/runtime trace → capture).