tooluniverse-infectious-disease

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and acts on untrusted public content (e.g., Phase 5 "Literature Intelligence" and associated code calling PubMed_search_articles, BioRxiv_search_preprints/EuropePMC, ArXiv_search_papers, web_search, ClinicalTrials.gov, OpenAlex, KEGG/Reactome) and uses those results to drive report conclusions and treatment/research recommendations, creating a clear pathway for indirect prompt injection via third‑party documents.