tooluniverse-sdk
Warn
Audited by Snyk on Apr 16, 2026
Risk Level: MEDIUM
Full Analysis
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 call public third‑party databases (e.g., OpenTargets_get_associated_targets_by_disease_efoId, ChEMBL_search_molecule_by_target, UniProt_get_entry_by_accession, get_latest_publications/PubMed) and to read and act on their returned data as part of workflows (drug_discovery_pipeline and tool execution), so untrusted public content can materially influence subsequent tool calls and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata