medical-research

Warn

Audited by Snyk on Feb 25, 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's required workflow (SKILL.md and README) instructs the agent to run .claude/skills/medical-research/pubmed_search.py to fetch and read PubMed records (https://pubmed.ncbi.nlm.nih.gov/), so it ingests open/public third‑party content which the agent must interpret and use to drive summaries and recommendations.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 12:09 PM