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 loading external public docs (e.g., WebFetch of https://raw.githubusercontent.com/.../README.md and https://modelcontextprotocol.io/sitemap.xml) and its evaluation tooling accepts arbitrary MCP server URLs (scripts/evaluation.py and connections.create_connection) whose tool lists and responses the agent will read and act on, exposing it to untrusted third-party content.
Audit Metadata