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 agents to fetch and read external public web resources (e.g., WebFetch of https://raw.githubusercontent.com/... and https://modelcontextprotocol.io/sitemap.xml) and the evaluation harness connects to arbitrary MCP server URLs (sse/http) and loads tool descriptions/results, so it ingests untrusted third‑party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:48 PM