gws-admin-reports

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the gws command-line tool to perform administrative tasks and retrieve reports from Google Workspace. This is the primary function of the skill and aligns with the vendor context.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external data from Google Workspace activity logs and usage reports, which provides a potential surface for indirect prompt injection.
  • Ingestion points: Data returned by API resources activities, customerUsageReports, entityUsageReports, and userUsageReport.
  • Boundary markers: No delimiters or explicit instructions are provided to the agent to disregard embedded content within the reports.
  • Capability inventory: Shell command execution via the gws binary.
  • Sanitization: No sanitization or validation of the retrieved report content is specified in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:42 PM
Security Audit — agent-trust-hub — gws-admin-reports