hypothesis-gen

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow has LiteratureScout retrieve public web/S2/arXiv content via the literature-search tool (and possible WebFetch fallback), ingesting verbatim snippets into litscout.json and thus into the agent context—an outsider-authored free-text source path.