ClawHub
Back to skill

Security audit

gogcli - Google Workspace CLI

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Google Workspace CLI skill, but it requires installing an external tool and granting sensitive Google account access.

Before installing, verify the gogcli repository or Homebrew tap, avoid sudo unless a global install is needed, enable only the Google APIs required for your task, and carefully confirm account identity, recipients, file paths, event details, and other parameters before any command that sends, uploads, creates, or modifies Google Workspace data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation trigger is extremely broad: 'Use when user asks to interact with Google services' could invoke this skill for many unrelated or sensitive requests across Gmail, Drive, Calendar, Contacts, and more. In an agent setting, overly broad routing increases the chance of unintended access to high-privilege Google data or execution of modifying actions without sufficiently narrow user intent.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The documentation describes authentication and commands for reading and modifying sensitive Google Workspace data, but it does not warn about data sensitivity, OAuth scope risk, or the need for confirmation before actions like sending email, uploading files, or creating events. This omission makes unsafe use more likely, especially in an automated agent context where users may not realize the breadth of account access granted.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.