mcp-builder

Warn

Audited by Snyk on Feb 27, 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 (Phase 1.2 and the Reference Files section) explicitly instructs the agent to fetch external public pages (e.g., https://modelcontextprotocol.io/sitemap.xml and raw.githubusercontent.com modelcontextprotocol SDK README.md files) and to use web search/WebFetch to load documentation, meaning the agent will read/interpret untrusted public web content that can materially influence subsequent tool design and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 04:45 AM