building-mcp-servers
Warn
Audited by Snyk on Feb 16, 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 explicitly instructs fetching and reading public web content (e.g., https://modelcontextprotocol.io/sitemap.xml and raw GitHub files like https://raw.githubusercontent.com/modelcontextprotocol/.../README.md), which are open third-party sources that the agent would ingest and could contain untrusted/user-generated content.
Audit Metadata