Google Workspace CLI

Security checks across malware telemetry and agentic risk

Overview

This is a transparent Google Workspace CLI guide with powerful account access, but its sensitive behavior is disclosed and gated by setup, scope, dry-run, and confirmation guidance.

Install only if you are comfortable letting an agent help operate Google Workspace through gws. Use minimum OAuth scopes, verify the CLI package source, keep credentials out of chat, prefer inspect or dry-run mode, limit MCP service exposure, and require explicit confirmation before sending, sharing, updating, or deleting data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The memory template recommends auto-activation for broad triggers such as 'gws' and generic 'Workspace API requests', which can match many ordinary user prompts and cause the skill to engage when not explicitly intended. In a skill that operates Google Workspace with OAuth-backed actions over Drive and Gmail, overly broad activation increases the chance of unintended access, confusing context carryover, or execution of higher-risk workflows without sufficiently clear user intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal