PrivateInvestigator

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

• Third-party content exposure detected (high risk: 0.85). The workflow ingests outsider-authored free text because it performs runtime web/social/public-record searches (e.g., via People Search Aggregators, LinkedIn/Facebook/Twitter pages, court/news listings) and then synthesizes the retrieved page content into the agent’s LLM context as part of the investigation results.