safe-git-guard
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill restricts specific Git commands (e.g., reset, clean, force push) rather than enabling arbitrary execution. It promotes safe usage through backups and confirmation steps.
- [DATA_EXFILTRATION] (SAFE): No network-related commands (curl, wget) or attempts to access sensitive directories (e.g., ~/.ssh, ~/.aws) are present.
- [PROMPT_INJECTION] (SAFE): The skill does not contain instructions to override the agent's core safety protocols or ignore previous instructions. It adds functional constraints intended to protect the user's environment.
- [EXTERNAL_DOWNLOADS] (SAFE): No external dependencies, package installations, or remote script executions are requested or performed.
- [PERSISTENCE] (SAFE): The skill does not modify system startup files, cron jobs, or shell profiles.
Audit Metadata