ClawHub
Back to skill

Security audit

Design Style

Security checks across malware telemetry and agentic risk

Overview

This is a frontend design-helper skill that broadly loads bundled style prompts, with no evidence of hidden data access, exfiltration, or destructive behavior.

Install this if you want automatic visual-design guidance during frontend/UI work. Be aware it may activate often and steer the agent toward a design-system aesthetic even when styling is only part of the task; review or avoid running the bundled helper scripts unless needed.

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 (2)

Vague Triggers

High
Confidence
89% confidence
Finding
The skill is configured to trigger proactively for virtually any frontend/UI-related request, which creates an overly broad activation surface. In an agent environment, broad auto-invocation can cause unintended prompt loading and context steering, increasing the chance that the model follows irrelevant or adversarially influenced skill instructions when a narrower, task-specific response would be safer.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The 'When to Use' section uses broad, somewhat ambiguous language such as web development and frontend requests without firm scope boundaries. This can lead to over-application of the skill and unnecessary prompt injection into unrelated coding tasks, though the content itself is design-oriented and does not directly enable code execution or data exfiltration.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
SKILL.md:109