tooluniverse-target-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries and ingests data from open/public third‑party sources (e.g., Path 0 OpenTargets endpoints, PubMed_search_articles/EuropePMC, PubChem_search_assays_by_target_gene, BindingDB_get_ligands_by_uniprot, DisGeNET_search_gene, HPA and GTEx APIs) and requires the agent to read and interpret that content (e.g., evidence grading, literature classification, and downstream recommendations), so untrusted external content can materially influence tool use and decisions.