astro-framework

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires using the Content Layer API with loaders and live loaders that fetch remote APIs and arbitrary URLs (see SKILL.md "Content Layer API (glob/file loaders, live loaders)" and references/content-collections.md examples showing custom loaders that call https://api.example.com/products and live loaders), so untrusted third‑party content is ingested and can influence rendering/behavior.