expansion-grant-guard
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script (guard.py) that handles grant lifecycle operations through a CLI interface. The script uses standard libraries and performs restricted file operations within the user's home directory.
- [DATA_EXPOSURE]: Grant data and audit logs are persisted in ~/.openclaw/skill-state/. The skill does not attempt to access credentials, sensitive configuration files, or external network resources.
- [REMOTE_CODE_EXECUTION]: The implementation is entirely local. It does not include patterns for downloading or executing remote code, nor does it use unsafe dynamic execution functions like eval().
Audit Metadata