hypothesis-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md, step "Conduct Comprehensive Literature Search") explicitly instructs using WebFetch with PubMed URLs and WebSearch to ingest public papers/preprints and web content, meaning the agent will fetch and interpret untrusted third-party web content that can directly influence hypotheses and subsequent actions.