Google Workspace CLI

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real Google Workspace helper, but it gives an agent live ability to create and change Drive, Docs, and Sheets data through an under-specified third-party CLI.

Review the npm package and source before installing, prefer providing your own Google OAuth client credentials instead of relying on defaults, and only let the agent run create/upload/write/append commands after you have confirmed the exact target file, folder, or spreadsheet and intended change.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly documents destructive and state-changing operations against Google Drive, Docs, and Sheets, including upload, create, append, and write actions, but provides no safety guidance, confirmation requirements, or warning that these commands modify remote user data. In an agent setting, this increases the risk of unintended file creation, overwrites, or data corruption if the model invokes these commands based on ambiguous prompts or hallucinated identifiers.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal