tooluniverse-cancer-variant-interpretation

Warn

Audited by Snyk on Mar 8, 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 explicitly fetches and ingests content from public third‑party data sources (e.g., CIViC, cBioPortal, OpenTargets, PubMed, ClinicalTrials.gov, FDA, DrugBank, UniProt, Reactome, GTEx) as required inputs in its SKILL.md workflow and uses that external free‑text and metadata to drive clinical recommendations and subsequent tool actions, so untrusted third‑party content can materially influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 01:17 PM