ClawHub
Back to skill

Security audit

Grok Image Tool Free

Security checks across malware telemetry and agentic risk

Overview

This image-generation skill is coherent, but needs review because it can control the live desktop/browser and save files with broad activation wording and limited safety boundaries.

Review before installing. Use it only for explicit Grok Imagine image-generation requests, preferably in an isolated browser/profile, and confirm the active window and save destination before allowing desktop mouse/keyboard automation.

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
90% confidence
Finding
The trigger condition is overly broad ('提升效率、自动化流程、批量处理、工作流优化时使用'), which can cause the skill to activate for generic user requests outside its narrow intended scope. In a skill that performs browser automation, desktop control, and local file saving, accidental invocation increases the chance of unintended clicks, file writes, or interactions with an already logged-in browser session.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs browser automation and desktop-level right-click/save actions to write files locally, but it does not warn users about the risks of interacting with a live desktop session, logged-in accounts, or overwriting/downloading unexpected content. Because the workflow relies on screen coordinates and UI state, a misfire could act on the wrong window or save unintended data to disk.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.