ClawHub
Back to skill

Security audit

gws

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clear Google Workspace CLI integration, but users should treat it as live access to real mail, files, calendars, and admin data once authenticated.

Install only if you want an agent or CLI to operate on real Google Workspace data. Use the narrowest OAuth scopes and MCP service list practical, prefer test accounts for automation, and use dry-run or read-only commands before allowing sends, shares, calendar writes, or admin actions.

SkillSpector

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
94% confidence
Finding
The skill documents powerful Google Workspace operations and MCP server exposure, but it does not prominently warn that the examples and agent-facing MCP mode can execute real, user-affecting actions such as sending email, modifying calendars, sharing Drive files, and changing admin resources. In an agent context, this omission increases the chance of unsafe use because users may interpret the examples as informational or low-risk when they are actually live operations against production Workspace data.

Static analysis

No suspicious patterns detected.