create-docs
Warn
Audited by Snyk on Apr 16, 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.md explicitly describes an MCP Server that "automatically exposes documents for the AI assistant" with endpoints like
list-pages/get-page(and the config references using NUXT_GITHUB_TOKEN and GitHub integration to fetch docs), meaning the agent will fetch and read repository- or web-hosted documentation (potentially public/user-contributed) which can directly influence its actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata