mcp-builder
Warn
Audited by Snyk on Nov 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow in SKILL.md:88 tells the agent to use web search and WebFetch to gather API documentation, which can return arbitrary outsider-authored web pages the agent must read, though the agent chooses which results to fetch.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata