ClawHub

Tailwind Design System

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only Tailwind CSS design-system skill with no executable behavior, credential use, persistence, or hidden data flow.

Install only if you want Chinese-first guidance for Tailwind CSS design-system architecture. Expect it to influence frontend styling decisions around tokens, variants, dark mode, and class organization, but it does not itself run code or access sensitive data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The activation text is broad enough to match many ordinary frontend or CSS-related requests, which can cause the skill to trigger outside its intended Tailwind design-system niche. Over-broad invocation can route user work through the wrong guidance, increasing the chance of irrelevant, lower-quality, or policy-misaligned assistance.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The skill body is written entirely in Chinese and effectively constrains behavior/output without stating any language-selection rule or fallback, which can cause user-language mismatch and unsafe task handling when the user expects another language. While not a classic security flaw, hidden locale constraints can degrade transparency, cause misunderstanding of instructions, and reduce operator oversight.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The skill description defines very broad activation triggers around common Tailwind and design-system topics, which can cause the skill to activate in routine frontend conversations without clear scope boundaries. In an agent ecosystem, over-broad triggering can lead to unnecessary context injection, incorrect tool/skill selection, and increased exposure to prompt-surface abuse if the skill is invoked when not actually needed.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal