ClawHub
Back to skill

Security audit

Google Workspace (No Cloud Console)

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Google Workspace integration, but it deserves review because it installs an unpinned third-party MCP server with persistent OAuth access and broad ability to read, send, modify, and delete Workspace data.

Review before installing. Only use this with a Google account you are comfortable granting broad Workspace access to, verify OAuth consent scopes during sign-in, and require explicit confirmation before any action that sends messages, modifies files or mail, changes calendar data, or deletes anything. If you stop using it, clear ~/.config/google-workspace-mcp/ and revoke the Google app access.

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
97% confidence
Finding
The skill explicitly states that OAuth credentials are stored under `~/.config/google-workspace-mcp/`, but it does not present this as a security warning or explain the sensitivity of those tokens. Users may unknowingly leave reusable access tokens on disk where other local processes, shared accounts, backups, or malware could access them, increasing the risk of account compromise.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill exposes many write-capable and communication-capable actions—such as sending Gmail, creating drafts, modifying emails, creating/updating/deleting calendar events, editing docs, and sending chat messages—without clear user-facing warnings about the potential for unintended external communication or destructive changes. In an agentic context, this raises the risk of accidental data modification, message sending, or privacy breaches if the skill is invoked with insufficient confirmation or oversight.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.