refactor-clean
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes common developer utilities including
grep,npm test,git, and PowerShell commands (Get-ChildItem,Measure-Object) to identify large files and duplicated code patterns. These operations are appropriate for the skill's stated purpose of code refactoring. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process source code files, which constitutes a surface for indirect prompt injection. A malicious file could contain instructions designed to influence the agent's behavior during the refactoring process. However, the instructions emphasize using existing tests (
npm test) as a safety net to verify that behavior is preserved. - [DATA_EXPOSURE]: The operations are confined to the project's source directory (
src/) and involve standard analysis of code structure. No access to sensitive credentials, SSH keys, or environment configuration files was found.
Audit Metadata