The Agent Skills Directory

[SAFE]: The skill content consists of architectural guidelines and evaluation cases. No signs of prompt injection, data exfiltration, or obfuscation were detected.
[SAFE]: All external URLs point to official developer documentation for React and Next.js, which are recognized as well-known and trusted services.
[NO_CODE]: No executable code, shell scripts, or third-party dependencies are included in the skill package.
[INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing plugin-based logic. It explicitly addresses security by recommending contract validation, runtime input checks, and proper resource disposal, which helps users avoid common injection vulnerabilities in their own implementations.

code-plugin-architecture