The Agent Skills Directory

[SAFE]: No security issues were detected. The skill's operations are consistent with its stated purpose as a developer assistant for Next.js projects.- [PROMPT_INJECTION]: The skill processes untrusted user code for review, which constitutes an indirect prompt injection surface. This is inherent to the skill's primary function and is mitigated by the agent's internal safety constraints.
Ingestion points: User-provided code snippets and project files for review and refactoring as specified in SKILL.md.
Boundary markers: None identified in the prompt templates.
Capability inventory: The skill utilizes Bash, Write, Edit, Read, Grep, and Glob tools for project interaction.
Sanitization: No explicit input sanitization or validation is implemented for code being reviewed.- [COMMAND_EXECUTION]: The skill implements a memory protocol that performs a file read operation using system tools.
Evidence: The SKILL.md file contains a mandatory protocol to execute cat .claude/context/memory/learnings.md to maintain state across interactions. This targets a non-sensitive internal context file.

nextjs-expert