mcp-builder
Warn
Audited by Snyk on Feb 15, 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 the agent to fetch and read external public web content (e.g., "Use WebFetch to load: https://modelcontextprotocol.io/llms-full.txt" and raw GitHub URLs, and to "use web search and the WebFetch tool as needed"), so the agent will ingest untrusted third‑party content from the open web as part of its workflow.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs WebFetch to load remote docs at runtime — e.g. https://modelcontextprotocol.io/llms-full.txt and https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md (and the TypeScript README) — which will be injected into the agent's context and can directly control prompts/instructions.
Audit Metadata