gws-admin-reports
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
gwscommand-line utility to perform administrative tasks and retrieve reports from Google Workspace. This utility is a project-specific tool required for the skill's intended functionality. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a consumer for external data from Google Workspace APIs, creating a potential surface for indirect prompt injection. 1. Ingestion points:
activities,customerUsageReports,entityUsageReports, anduserUsageReportresources inSKILL.md. 2. Boundary markers: Not present. 3. Capability inventory: Execution ofgwsCLI commands. 4. Sanitization: Not present in the skill instructions. The risk is considered minimal as the data consists of system-generated audit logs.
Audit Metadata