ClawHub
Back to skill

Security audit

Pixelvault Upload

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward helper for uploading user-selected image files to a public PixelVault CDN, with the main risk being that uploaded images become permanent public links.

Install only if you want Codex to upload image files to PixelVault for public sharing. Review screenshots, diagrams, and build artifacts for secrets or private information before upload, because the resulting CDN links are described as permanent and globally cached.

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
91% confidence
Finding
The skill advertises very broad triggers such as 'attach this screenshot to the PR/issue' and generally applies whenever an image is generated or saved. That can cause the agent to upload files without a sufficiently explicit user decision, which is risky because the destination is a public CDN and the action transfers local artifacts off-system.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill repeatedly describes returning CDN URLs but does not clearly warn that uploads become publicly accessible and effectively permanent. In context, this is especially dangerous because screenshots, diagrams, and build artifacts often contain sensitive information, so users may unknowingly expose internal data, credentials, or proprietary content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.