using-gws-toolkit
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a high-level router that maps user intents to specific tools and scripts within the Google Workspace ecosystem. It does not contain any executable code, shell commands, or external network requests in its primary instructions.
- [SAFE]: The routing logic is based on explicit keyword matching and the inspection of a local configuration file (
slide-plan.json). The analysis of the ingestion point shows it is used only for internal state management (determining the backend target) and does not involve unsafe interpolation into shell commands or API calls. - [SAFE]: The skill incorporates security best practices by recommending the use of 'safety wrappers' (e.g.,
scripts/gws/gmail-confirm-send.sh) that require human confirmation for write-side operations such as sending emails or modifying files. - [SAFE]: No obfuscation, data exfiltration patterns, or unauthorized privilege escalation attempts were detected. The use of multilingual keywords (English, Japanese, Chinese) is consistent with the stated purpose of a global entry-point router.
Audit Metadata