mcp-builder
Warn
Audited by Snyk on Apr 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow and Reference Files explicitly instruct the agent/developer to fetch public web content (e.g., "https://modelcontextprotocol.io/sitemap.xml" and raw.githubusercontent.com SDK READMEs) and to use web search/WebFetch as part of required Phase 1 research and documentation-inspection steps, meaning the agent will read and act on untrusted public web pages whose content can influence tool design and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata