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
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:52 PM