The Agent Skills Directory

[SAFE]: The skill is a set of text-based instructions for code review. It does not invoke any tools, perform network requests, or access sensitive files.
[DATA_EXPOSURE]: There are no patterns indicating data exfiltration or access to sensitive local environment variables or credentials.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute any external scripts or packages.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code provided by the user (ingestion point: target file/diff). However, it lacks any high-risk capabilities (capabilities inventory: none) to act upon malicious instructions that might be embedded in the code being reviewed. There are no boundary markers or sanitization steps mentioned, but without dangerous tools, the risk is negligible.

discuss-code