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 for find-anyone ingests outsider-authored free text by searching and reading public-facing sources (e.g., “professional networks,” “published output,” “regulated-role registers,” and especially “social and behavioural” via hunt-a-handle/pattern-of-life-from-socials), which can include attacker-submitted text that the agent consumes during investigation.