data-freshness-check

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires the agent to "Verify each fact on ≥2 independent sources" and to record the "exact URL" in Step 3 and its Source Authority Hierarchy (including public sites like entity websites, OpenCorporates, press articles, blogs and registries), so the agent will fetch and read untrusted public web content that can change verification outcomes and downstream actions.