deep-research

Warn

Audited by Snyk on Mar 1, 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). SKILL.md explicitly directs the agent to perform systematic searches and ingest findings from public third‑party databases (e.g., "Key Databases: PubMed, arXiv, Google Scholar, Semantic Scholar") and requires reading/interpreting those sources to produce citations and drive recommendations, so untrusted external content could influence agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 03:47 PM