tanstack-start

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

• Third-party content exposure detected (high risk: 0.70). The skill includes examples that fetch and consume external, arbitrary URLs and user content (e.g., rules/auth-patterns.md shows createIsomorphicFn fetching "https://api.example.com/user" and rules/seo-head-management uses loaderData from fetchPost(params.slug) to populate head/meta), so the agent is expected to read and interpret third-party content at runtime.