mcp-builder
Warn
Audited by Snyk on May 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly instructs fetching and parsing public web content (see SKILL.md Phase 1.2: "https://modelcontextprotocol.io/sitemap.xml" and instructions to fetch .md pages and raw GitHub READMEs like https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md), meaning untrusted third‑party pages are consumed and can influence tool choices and agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata