gat-workflow-start
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates exclusively within the
gat/directory for repository state inspection, minimizing the scope of file access. - [SAFE]: Tool usage is restricted to
Read,Glob,Grep, andAskUserQuestion. These tools are used for diagnostic and interaction purposes only and do not allow for code execution or network communication. - [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the skill's instructions or metadata.
- [SAFE]: The skill recommends further actions to the user in the form of other skill commands but does not attempt to execute them autonomously or without user oversight.
Audit Metadata