anthropic-mcp-builder
Warn
Audited by Snyk on Mar 7, 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 and referenced guides explicitly instruct the agent to fetch and read public web documentation (e.g., "Start with the sitemap at https://modelcontextprotocol.io/sitemap.xml" and "Use WebFetch to load https://raw.githubusercontent.com/.../README.md"), so the agent will ingest untrusted public third‑party content that can influence tool selection and next actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The evaluation harness can connect at runtime to a remote MCP server URL (e.g., https://example.com/mcp) and calls connection.list_tools to fetch tool definitions which it passes into the model as "tools", meaning remote content from that URL can directly control agent prompts/behavior.
Audit Metadata