group-onboarding

Warn

Audited by Snyk on May 12, 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). The SKILL.md explicitly instructs the agent to list and read a team's Yuque knowledge bases (via yuque_list_repos, yuque_get_toc, and yuque_get_doc), ingesting user-generated third‑party documents that directly influence prioritization, summaries, and subsequent actions.

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill calls the external yuque-mcp tools at runtime (notably yuque_get_doc via the yuque-mcp server) to fetch raw Yuque documents and inject their content into the agent's context to drive the generated onboarding guide, which meets the criteria for external content directly controlling prompts.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 12, 2026, 09:11 AM
Issues
2
Security Audit — snyk — group-onboarding