vitepress

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

• Third-party content exposure detected (high risk: 0.90). The skill's documentation and workflow explicitly describe build-time data loaders and dynamic path loaders that fetch remote APIs and CMS content (see references/features-data-loading.md and references/features-dynamic-routes.md where examples call fetch(...) and inject remote "content" into templates), which means the agent ingests untrusted third‑party content that can influence page generation and behavior.