nextjs-setup

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly runs "bunx create-next-app@latest" (fetching scaffold/template code from the public npm registry) and requires inspecting the generated package.json and potentially starting the dev server, so the agent will ingest and act on untrusted third-party content produced/fetched from the open web.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill runs the command "bunx create-next-app@latest" at runtime, which fetches and executes remote package code from the npm registry (i.e., external code) and is relied on as a required dependency.