tooluniverse-sdk

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md and REFERENCE.md show example workflows that call public third-party sources (e.g., PubMed_search_articles, UniProt_get_entry_by_accession, ChEMBL_search_molecule_by_target, OpenTargets_get_associated_targets_by_disease_efoId) and explicitly ingest and act on those results as part of pipelines, so untrusted external content can influence tool use and next actions.