fact-checker

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Verification Process directs the agent to "Check authoritative sources" and "Evaluate Available Evidence," and the "Source Quality Hierarchy" explicitly includes social media/blogs (public, user-generated) — indicating the agent will ingest and act on open/public third‑party content, which could enable indirect prompt injection.