bioinformatician

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill's Data Provenance / "Data Sources" documentation and examples (e.g., the GEO wget download line in the "Document data sources" section and links to GENCODE) explicitly instruct downloading and loading public repository datasets (GEO, GENCODE) so the agent will ingest untrusted, user-submitted third‑party data and metadata as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 06:30 AM