next-cache-components-adoption

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to read Next.js documentation and error message pages from nextjs.org during the build and dev loop, which involves fetching external web pages.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references external GitHub repositories via https://github.com/vercel/next.js/tree/canary/skills/... URLs for optional skill installation at runtime, which constitute common/reputable unofficial or weak external dependencies under the dependency gate.