notion-translate-skill

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). Outsider-authored Notion page content is fetched at runtime via fetch-texts → notionRequest(..., GET /pages/{pageId}) and fetchAllBlocks(...), then the extracted text fields are output as JSON for the AI translation step (indirect prompt injection risk).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill's runtime command runs (test -d node_modules || npm install) && npx -y tsx ..., which will fetch and execute remote npm packages (see package-lock resolved URLs like https://registry.npmmirror.com/...), so external code is downloaded and executed at runtime as a required dependency.