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
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:05 PM