tanstack-start-migration

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

• Third-party content exposure detected (high risk: 0.95). The skill’s runtime path fetches TanStack documentation via the provided public URLs (e.g., https://tanstack.com/llms.txt and the “Migrate from Next.js” page) and ingests that fetched free text into the agent’s LLM context, which is outsider-authored web content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs fetching https://tanstack.com/llms.txt at runtime as an "LLM reference" (used to populate the agent's documentation index and thus directly influence prompts/context), making it a runtime external dependency that controls prompts.