doublecheck

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

• Third-party content exposure detected (high risk: 0.90). The skill's documented workflow (see "Layer 2: Source Verification" and the Active Mode instructions) explicitly requires running web_search and ingesting/assessing URLs from the open web to verify claims, so the agent will fetch and interpret arbitrary third‑party content that can materially change its verification judgments and behavior.