ClawHub
Back to skill

Security audit

极简设计系统免费版

Security checks across malware telemetry and agentic risk

Overview

This is a design-system guidance skill that can guide local frontend file changes and simple commands, but the inspected artifact shows no hidden data collection, persistence, or destructive behavior.

Install this as a frontend design-system helper, not as a general automation or deployment tool. Expect it may suggest editing local Tailwind/CSS/component files and running simple setup or troubleshooting commands; review those changes and commands before allowing them. It does not require API keys and the inspected artifact does not show hidden persistence or data exfiltration.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill declares `exec` capability even though its stated purpose is design-system guidance and local configuration advice. Unnecessary command execution expands the attack surface: an agent could be induced to run shell commands or modify the environment without a clear functional need, especially since the document also includes command snippets and write-capable workflow framing.

Context-Inappropriate Capability

Low
Confidence
81% confidence
Finding
The error-handling section instructs use of `ping` and firewall/proxy diagnostics, which are outside the core scope of a local design-system integration skill. Even though the commands are simple, they normalize network-oriented execution in a skill that otherwise should not need network diagnostics, increasing the chance of unnecessary command use or scope creep.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill advertises an overly broad activation scope, including generic coding, debugging, testing, deployment, enterprise-team, and automation-workflow scenarios unrelated to a minimalist design-system guide. Overbroad triggers can cause the agent to invoke this skill in inappropriate contexts, where its write/exec affordances and vague 'core processing' language may lead to unintended file changes or command execution.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill combines `write` and `exec` capabilities with procedural language about performing operations and applying configuration, but it does not present a clear upfront warning that project files may be modified or commands may be executed. In an agent setting, lack of explicit consent boundaries can mislead users into invoking potentially state-changing actions they did not expect.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.