ClawHub
Back to skill

Security audit

中文UI/UX设计智能

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Chinese UI/UX design skill with broad design triggers, but it does not request sensitive access or perform hidden actions.

Install this when you want Chinese-localized UI/UX defaults such as Chinese fonts, local platform conventions, and Chinese-market color or interaction guidance. For global or non-Chinese products, invoke it deliberately or be ready to override its locale assumptions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation conditions are broad enough to match many ordinary design, frontend, and review requests, which can cause the skill to trigger when the user did not explicitly ask for it. In an agent setting, overbroad auto-activation can override user intent, inject unnecessary guidance, or steer outputs toward this skill’s defaults without clear consent.

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
Hard-coding the skill language to zh-CN without describing user override behavior can cause the agent to respond in Chinese even when the user prefers another language. This is primarily a policy and usability risk, but in multi-step workflows it can also lead to misunderstandings, incorrect implementation, or inaccessible outputs for non-Chinese users.

Natural-Language Policy Violations

Medium
Confidence
77% confidence
Finding
The content repeatedly mandates Chinese UI text and related conventions without stating that this applies only to Chinese-market products or when the user requests Chinese localization. That can inappropriately bias generated interfaces, causing localization errors, audience mismatch, and accidental replacement of user-specified language or branding requirements.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list contains very broad, common terms such as "设计", "UI", "UX", "界面", and "布局", which are likely to match ordinary user conversations outside a deliberate invocation context. This can cause unintended activation of the skill, increasing the chance that the agent injects its design-specific behavior or prompts into unrelated workflows and expands the attack surface for prompt/skill hijacking.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.