The Agent Skills Directory

[PROMPT_INJECTION]: No malicious injection patterns, such as instructions to override safety filters or disregard prior rules, were detected. The skill consists entirely of technical best practices for web development.
[DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive file paths (e.g., .ssh, .aws) were found. The code examples use placeholder domains like 'api.example.com' or 'api.store.com' which are standard for documentation.
[OBFUSCATION]: The content is presented in clear Markdown and TypeScript. No Base64-encoded payloads, zero-width characters, or homoglyph-based obfuscation techniques were identified.
[REMOTE_CODE_EXECUTION]: The skill does not contain patterns for downloading and executing remote scripts (e.g., curl | bash). It provides guidance on configuring 'serverExternalPackages', which is a standard Next.js configuration for native Node.js modules.
[COMMAND_EXECUTION]: Shell commands are only present in documentation code blocks for build and development purposes (e.g., 'next dev', 'next build'). No unauthorized or malicious command execution patterns were found.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The agent ingests these rules to apply them to a user's codebase during refactoring or code generation.
Boundary markers: Not applicable, as the skill defines the logic the agent should follow rather than processing external runtime data.
Capability inventory: The skill guides an agent that likely has file system access and shell capabilities to perform development tasks.
Sanitization: The skill provides correct coding patterns (e.g., 'use cache', 'revalidateTag') which help in building secure and performant applications.
[DYNAMIC_CONTEXT_INJECTION]: No '!'backtick' command syntax was found in the SKILL.md file, ensuring no hidden commands are executed at load time.

nextjs