yuque-personal-smart-search

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill calls external yuque-mcp endpoints (via the runtime tools yuque_search and yuque_get_doc) to fetch user Yuque documents at runtime, and that fetched content is injected into the agent's context and directly controls the agent's responses.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 07:18 AM