ClawHub
Back to skill

Security audit

Design Assets Index

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only index of design resource links, with no code execution, credential access, persistence, or hidden behavior found.

Installers should treat this as a curated list of third-party design links. Review license terms and privacy practices on any linked site before downloading or using assets commercially, but the skill itself does not request sensitive access or run code.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger guidance is unusually broad: it says to use the skill whenever a user needs a ready-made asset, including vague requests like 'I need an image' or 'find me an icon'. In an agent setting, this can cause over-invocation on common queries, leading the model to fetch external resource suggestions when the user may have wanted original generation, narrower help, or a different workflow.

VirusTotal

2/63 vendors flagged this skill as malicious, and 61/63 flagged it as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.