ClawHub
Back to skill

Security audit

ai-wallpaper-skill

Security checks across malware telemetry and agentic risk

Overview

This is a coherent AI wallpaper skill that sends prompts to Baidu AIStudio, saves one generated image locally, and changes the desktop wallpaper as advertised.

Install only if you are comfortable sending wallpaper prompts to Baidu AIStudio using your access token and allowing the skill to replace your current desktop wallpaper. Use a limited-purpose token, avoid sensitive prompt content, and ask the agent to preview or confirm before applying changes if that matters to your workflow.

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 (4)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README explicitly documents use of an external AI endpoint but does not clearly warn users that prompts and related data will be transmitted off-device to a third-party service. For a wallpaper-generation skill, users may submit sensitive or personal text prompts, so the missing disclosure creates a real privacy and consent risk even though the behavior appears functional rather than malicious.

Missing User Warnings

Low
Confidence
89% confidence
Finding
The README states that the skill sets the system wallpaper on Windows and macOS, but it does not prominently warn that running the skill will modify the user's desktop environment. This is a real but lower-severity issue because the behavior is expected for the skill's purpose, yet explicit notice and consent are still important before making visible system changes.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases are broad enough to activate on common requests like changing backgrounds or generating a desktop image, which can cause the skill to run in situations where the user did not intend automatic system modification. Because the skill both generates content and changes the OS wallpaper, overbroad invocation increases the chance of surprising or unauthorized state changes on the user's machine.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill states that it will persist the image but does not clearly warn that execution will automatically change the user's active system wallpaper on Windows or macOS. Automatic modification of a user-visible system setting without prominent disclosure or explicit consent is risky because it can surprise users, disrupt workflows, or be abused through ambiguous prompts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.