astro

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs ingesting external, potentially untrusted content (e.g., fetch('https://api.example.com/posts') in references/ssg-patterns.md and a custom loader fetching 'https://api.example.com/products' in references/content-collections.md) and uses that content in required workflows like getStaticPaths and rendering post.content (set:html), so third‑party data can influence routing, rendering, and runtime behavior.