find-anyone

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests outsider-authored free text by performing open-web searches and fetching/reading arbitrarily authored third-party profiles/content (e.g., professional networks, press, social handles, and other “published output” layers) using provided selectors, so attacker-controlled text can be consumed without first selecting a specific item.