google-workspace
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a setup script (
setup.py) with an--install-depsflag intended for installing necessary libraries. While specific packages are not enumerated in the provided files, this is standard practice for API integrations. - [COMMAND_EXECUTION]: Operates by executing local Python scripts (
scripts/google_api.py) and potentially thegwsCLI tool to perform Workspace actions. - [INDIRECT_PROMPT_INJECTION]: As the skill ingests data from external sources like Gmail messages and Drive files, it is subject to indirect prompt injection risks.
- Ingestion points: Gmail messages, Drive file contents, and Google Sheets data.
- Boundary markers: None explicitly defined in the instruction text.
- Capability inventory: Capability to send/reply to emails, create/delete calendar events, and modify sheets.
- Sanitization: Rule 1 explicitly mandates user confirmation before performing any write or delete actions, providing a strong human-in-the-loop safeguard.
Audit Metadata