tooluniverse-drug-target-validation

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and ingest open public content (e.g., OpenTargets_get_*, PubMed_search_articles, ChEMBL_get_target_activities, PubChem_get_assay_summary, BindingDB_get_ligands_by_uniprot, GTEx/HPA/Reactome/AlphaFold calls) and uses that evidence directly to compute scores and GO/NO-GO recommendations, so untrusted third‑party content can materially influence subsequent decisions and tool use.