reference-class-forecasting

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

• Third-party content exposure detected (high risk: 0.90). This skill's "Step 3: Search for Historical Data" (SKILL.md) explicitly instructs the agent to perform web searches and use "web search for published statistics" with arbitrary search queries and sources, meaning the agent will fetch and read open/public third‑party content (web pages/reports) which can include untrusted, user-generated material.