gws-admin-reports
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves audit logs and usage reports from Google Workspace, which are then processed by the agent, representing a potential surface for indirect prompt injection.
- Ingestion points: The methods
activities list,customerUsageReports get,entityUsageReports get, anduserUsageReport getas described inSKILL.mdingest external data. - Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded content in the logs.
- Capability inventory: Capabilities are limited to the
gwsbinary for administrative reporting and discovery. - Sanitization: Absent; the skill does not define sanitization or validation logic for the retrieved audit data.
- [SAFE]: The skill follows established patterns for administrative CLI wrappers. No instances of obfuscation, hardcoded credentials, or unauthorized command execution were found.
Audit Metadata