mcp-builder
Warn
Audited by Snyk on Mar 10, 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 the agent to fetch and load public third‑party resources (e.g., https://modelcontextprotocol.io/sitemap.xml and raw GitHub READMEs such as https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md) and to "use web search and WebFetch as needed," meaning untrusted open‑web content will be ingested and can materially influence tool selection and actions.
Audit Metadata