mdx

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md "Remote MDX" section explicitly fetches posts from an external API (fetch(https://api.example.com/posts/${slug})) and passes post.content into MDXRemote for rendering, which ingests untrusted third‑party MDX/JSX that can influence rendered behavior and downstream actions.