The Agent Skills Directory

[SAFE]: The skill serves as a guide for performing code reviews, focusing on maintainability, stability, and security best practices within a specific codebase.
[DATA_EXFILTRATION]: No exfiltration risks were detected. The instructions explicitly advise against logging sensitive information such as authtokens, authorization headers, or management tokens.
[PROMPT_INJECTION]: The skill does not contain any instructions aimed at bypassing safety filters or overriding agent behavior.
[REMOTE_CODE_EXECUTION]: There are no patterns suggesting the download or execution of remote code. It references standard project build commands like npm run build within a development context.
[EXTERNAL_DOWNLOADS]: The skill does not reference or attempt to download any external resources or dependencies from untrusted sources.

code-review