ClawHub
Back to skill

Security audit

Tmp.4g8z2dHt1r

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Google Workspace automation wrapper that uses a local gogcli login, with no hidden code or install-time behavior in the inspected artifact.

Install this only if you want agents to use your locally authenticated gogcli Google account for Workspace automation. Confirm the target document, sheet, Drive item, class, and account before edits, uploads, downloads, permission changes, grading, or roster-related actions.

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
78% confidence
Finding
The trigger text is broad enough that an agent may invoke this skill for many loosely related requests involving Google Workspace, even when the user did not intend account-backed automation. In this context, overbroad activation is risky because the skill can operate against an authenticated local Google account and may perform read or write actions on Docs, Sheets, Drive, Slides, or Classroom resources.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documentation omits an explicit warning that it will use the locally authenticated gogcli account and may modify or access sensitive Google Workspace content. In this skill context, that omission is more dangerous because the tool spans multiple high-value services and can read, alter, upload, download, or manage permissions on user data, increasing the chance of surprising or unauthorized actions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.