tooluniverse-infectious-disease

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests open/public third-party content (e.g., PubMed, BioRxiv, MedRxiv, ArXiv, UniProt, ChEMBL, NCBI Taxonomy, KEGG, ClinicalTrials.gov) as required workflow steps (Phase 1–5) and uses that untrusted/user-generated material to drive target selection, docking, literature synthesis, and recommendations, so external content can materially influence agent actions.