tooluniverse-pharmacovigilance
Warn
Audited by Snyk on Mar 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and ingest open/public third‑party data (e.g., FAERS via
FAERS_count_reactions_by_drug_event, DailyMed labels viaDailyMed_search_spls/DailyMed_get_spl_by_set_id, PharmGKB viaPharmGKB_search_drug, and literature/preprints viaPubMed_search_articlesand EuropePMC/BioRxiv/MedRxiv`) as mandatory inputs that the agent must read and interpret to calculate signals and drive recommendations, so untrusted third‑party content can materially influence tool use and next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata