skills/finpeakinc/gws-cli/gws-shared/Gen Agent Trust Hub

gws-shared

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official Google Workspace CLI repository (googleworkspace/cli). This is a well-known service and an appropriate source for this type of tooling.
  • [DATA_EXFILTRATION]: Documents standard CLI functionality for managing files, including --upload for multipart uploads and --output for saving binary data. These patterns are consistent with legitimate administrative tasks for Google Workspace.
  • [INDIRECT_PROMPT_INJECTION]: The skill serves as a reference for tools that ingest and process data from external Google services.
  • Ingestion points: CLI command outputs from Google Workspace resources (e.g., Sheets, Drive).
  • Boundary markers: None explicitly mentioned in the syntax reference.
  • Capability inventory: Includes file writing, uploads, and data pagination.
  • Sanitization: The documentation proactively recommends using the --sanitize flag for Model Armor screening to mitigate risks associated with untrusted content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 08:23 AM
Security Audit — agent-trust-hub — gws-shared