mcp-builder
Warn
Audited by Snyk on Mar 4, 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 explicitly instructs the developer/agent to fetch and read public web pages (e.g., "https://modelcontextprotocol.io/sitemap.xml" and raw.githubusercontent.com README.md links) as required Phase 1 steps, meaning the agent will ingest open/public, potentially user-authored content and use it to plan and drive implementation decisions (not just display), which could allow indirect prompt injection.
Audit Metadata