ClawHub
Back to skill

Security audit

Google Workspace CLI (gog)

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Google Workspace CLI helper, but it requires broad Google account access and can perform visible or destructive Workspace actions.

Install only if you trust the external gog CLI package. During setup, review the Google OAuth scopes carefully, keep client secrets and tokens out of chats and repositories, and require explicit confirmation before sending email, creating events, or changing or clearing Workspace data.

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 (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill instructs users to configure OAuth credentials and authorize broad Google Workspace scopes without warning that the client secret file and granted tokens can expose highly sensitive Gmail, Drive, Calendar, Contacts, Sheets, and Docs data. In an agent context, users may follow setup steps without understanding the security implications, increasing the risk of overbroad access and mishandling of credential material.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill lists state-changing commands such as Gmail send, Sheets update/append/clear, and potentially event creation-oriented workflows with little or no warning about irreversible or user-visible effects. In an agent setting, examples often become copied actions, so omission of confirmation guidance around destructive or modifying operations raises the chance of accidental data loss, unwanted communications, or corruption of user records.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.