ClawHub
Back to skill

Security audit

Google Workspace Ops

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly described Google Workspace helper that can edit shared files, so users should confirm changes before applying them.

Install only with Google credentials that have the minimum needed access. Treat write operations as live changes to shared Workspace files: review the selected file, ranges, and planned edits first, and use copies or version history for important documents.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases are broad enough to match routine Google Workspace requests, which can cause the skill to activate in situations where the user did not explicitly intend to invoke a document-modifying workflow. In this skill's context, that is more dangerous because it is designed to locate, edit, restructure, merge, and clean shared files in place across Drive, Docs, Sheets, and Slides, increasing the chance of unintended changes to collaborative assets.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill describes workflows that can update documents, spreadsheets, and slides in place, but it does not prominently warn users that shared Google Workspace files may be modified directly. This is dangerous because users may treat the skill as read-only or advisory, while it can perform destructive or hard-to-reverse operations like cleanup, restructuring, merge recommendations, or edits on canonical shared files.

Static analysis

No suspicious patterns detected.