The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill's instructions or logic.
[PROMPT_INJECTION]: No evidence of instructions designed to bypass safety filters, extract system prompts, or override agent constraints was found.
[DATA_EXFILTRATION]: The skill reads local files for the purpose of code review but lacks tools or commands for network communication or data exfiltration.
[REMOTE_CODE_EXECUTION]: No patterns involving the download or execution of remote scripts or the installation of unverified dependencies were detected.
[COMMAND_EXECUTION]: The skill uses standard search utilities like grep and glob to navigate the codebase, which is appropriate for its stated purpose. No high-risk command execution patterns (e.g., sudo, privilege escalation) are present.

code-reviewer