gws-groupssettings
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
gwsbinary on the host system to interact with Google Workspace APIs, including commands for discovery (gws schema) and management (gws groupssettings). - [INDIRECT_PROMPT_INJECTION]: The skill processes Google Groups settings (names, descriptions, and configurations) which are externally controlled and could contain malicious instructions.
- Ingestion points: Administrative data is ingested via the
groups.getmethod (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the retrieved API responses.
- Capability inventory: The agent possesses the capability to execute shell commands and modify Google Workspace configurations via the
gwstool. - Sanitization: No sanitization or validation of the retrieved API data is specified in the skill's logic.
Audit Metadata