The Agent Skills Directory

[SAFE]: Analysis of the skill instructions and referenced documents did not reveal any malicious patterns, privilege escalation, or persistence mechanisms.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied source code for review and refactoring tasks. This is an inherent property of the skill's purpose rather than a malicious implementation.
Ingestion points: User-provided Next.js code for review and refactoring (SKILL.md).
Boundary markers: None explicitly defined in the instructions.
Capability inventory: Suggests execution of local build, lint, and migration tools (workflows.md).
Sanitization: No automated sanitization is defined within the skill content.
[EXTERNAL_DOWNLOADS]: The documentation includes a reference to using @next/codemod via npx, which is an established tool provided by Vercel for Next.js version migrations.

nextjs