gws-admin-reports
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
gwscommand-line utility to interact with Google Workspace APIs. This is the core functionality of the skill and is documented for use in retrieving administrative data. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from Google Workspace APIs, which could potentially contain attacker-controlled content within logs or reports.
- Ingestion points: Data is ingested through API resources including
activities.list,customerUsageReports.get,entityUsageReports.get, anduserUsageReport.getinSKILL.md. - Boundary markers: No explicit boundary markers or isolation instructions for external data are provided in the skill instructions.
- Capability inventory: The skill is capable of executing shell commands via the
gwsCLI as detailed inSKILL.md. - Sanitization: There is no evidence of data sanitization or filtering performed on the API responses before they are processed by the agent.
Audit Metadata