mcp-builder
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: 0.90). The skill explicitly instructs agents to fetch and load public web content (e.g., "https://modelcontextprotocol.io/sitemap.xml", raw.githubusercontent.com SDK READMEs, and "use web search and WebFetch") and its evaluation harness and connection code accept arbitrary SSE/HTTP MCP server URLs, meaning the agent will read and interpret untrusted third-party content.
Audit Metadata