ClawHub
Back to skill

Security audit

Gws Admin

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Google Workspace admin command reference, but it exposes high-impact account and security administration actions without enough built-in safety scoping.

Install only for agents you trust to operate Google Workspace administration. Use a least-privilege Google account, require explicit human approval before deletes, role changes, 2-Step Verification changes, token operations, verification-code access, device wipes, or user sign-outs, and prefer read-only inspection commands before mutations.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Credential Access

High
Category
Privilege Escalation
Content
### tokens

  - `delete` — Deletes all access tokens issued by a user for an application.
  - `get` — Gets information about an access token issued by a user.
  - `list` — Returns the set of tokens specified user has issued to 3rd party applications.
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High
Category
Privilege Escalation
Content
### tokens

  - `delete` — Deletes all access tokens issued by a user for an application.
  - `get` — Gets information about an access token issued by a user.
  - `list` — Returns the set of tokens specified user has issued to 3rd party applications.

### twoStepVerification
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill enumerates many destructive Google Workspace admin operations such as deleting users, groups, domains, tokens, devices, and role assignments, but provides no overarching safety guidance about confirmation, least privilege, backup, or recovery implications. In an admin-oriented skill, this omission increases the likelihood of accidental destructive use and unsafe delegation through the agent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This section includes highly sensitive account-security actions such as turning off 2-Step Verification, making a user a super administrator, signing users out, generating backup verification codes, and deleting or updating user accounts without explicit warnings. Because this is an admin skill for a real enterprise control plane, omission of targeted warnings materially raises the risk of privilege escalation, account takeover assistance, or disruptive misuse.

Static analysis

No suspicious patterns detected.