scenario-war-room

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

• Third-party content exposure detected (high risk: 1.00). The skill's Multi-Agent Analysis (Step 2 "Explore" Task) explicitly instructs agents to "Research... Find 3-5 case studies or public examples" and "Return ... with source," which requires fetching and interpreting open/public third‑party content (case studies, news, or web sources) that could materially influence decisions.