hypothesis-generation

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to retrieve and read external literature via "WebFetch with PubMed URLs" and general "WebSearch" for papers, preprints and web content, i.e., open/public third‑party sources that the agent will ingest and interpret.