claim-investigation

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to investigate "social media and other sources" and to use a search strategy that cross-references public news sites, social media, and public documents (e.g., ".gov, electoral bodies" and "contemporary news reports"), so the agent is expected to fetch and interpret untrusted third-party web/user-generated content as part of its workflow.