TanStack Start

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly monitors and fetches public third-party content — e.g., GitHub releases and Issue #5734, npm package metadata via npm view, and external blog/Cloudflare docs — which are untrusted/public (user-generated issues/posts) and the agent is expected to read and interpret them as part of its monitoring workflow.