vitepress

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

• Third-party content exposure detected (high risk: 0.90). The skill documentation shows build-time loaders and dynamic routes that fetch and ingest remote, potentially user-generated content (e.g., references/features-data-loading.md with async fetch('https://api.example.com/data'), references/features-dynamic-routes.md fetching from 'https://cms.example.com/posts' and returning content for templates, and core-config.md's dynamic config fetch example), so the agent would read/interpret untrusted third‑party content as part of its workflow.