design-judge-skills

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow for award verification explicitly involves searching/navigating official award galleries and scraping official detail pages, and while it also mentions third-party sites for discovery, it does not indicate that the agent ingests arbitrary outsider-authored free text without first selecting specific items to fetch.