tooluniverse

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md shows the agent invoking public third‑party databases and tools (e.g., OpenTargets, PubChem, UniProt, PDB, ChEMBL, ZINC) via tu.run (examples like OpenTargets_get_associated_targets_by_disease_efoId, AlphaFold_get_structure, ZINC_virtual_screening), which ingests external content that the agent reads and uses to drive subsequent tool choices and workflow decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 01:30 AM