mcp-builder
Warn
Audited by Snyk on Feb 20, 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 (Phase 1.2 and the "Documentation Library" sections) explicitly instructs the agent/developer to fetch public pages such as https://modelcontextprotocol.io/sitemap.xml and raw GitHub URLs (e.g., https://raw.githubusercontent.com/modelcontextprotocol/.../README.md), so the agent is required to load and interpret open/public third‑party content that can materially influence tool design and actions.
Audit Metadata