dr-midas
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: 0.80). The SKILL.md workflow (Step 2) explicitly instructs the agent to call pubmed_search and — if PubMed yields no results — "使用 WebSearch 或其他搜索工具替代", which requires fetching and interpreting open/public web content (arbitrary URLs) that can be untrusted or user-generated and could therefore influence the agent's decisions.
Audit Metadata