ClawHub
Back to skill

Security audit

Ui Ux Toolkit Free

Security checks for vulnerabilities and agentic risk

Overview

The skill is a UI/UX lookup guide, but it requests command execution while the referenced local CLI tool is not included and it includes privileged install guidance, so it needs user review before installation.

Review this skill before installing. Only use it if you can verify the intended scripts/search.py and design data source, do not let an agent run relative scripts from an untrusted project, and require explicit approval before any sudo or package-manager command is executed.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (6)

Chaining Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

The chained command sudo apt update && sudo apt install python3 encourages immediate sequential execution of privileged operations without an explicit review checkpoint between them. In an agent/tool-use setting, command chaining can make it easier to execute impactful system changes automatically and reduces opportunities to inspect failures or unexpected behavior before proceeding.

Content

Scanner excerpt · SKILL.md (reported line 315)May include surrounding context.

md
brew install python3

# Ubuntu/Debian
sudo apt update && sudo apt install python3

# Windows
winget install Python.Python.3.12

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The entire skill description and operational guidance are written in Chinese, and the file does not indicate that language is selectable or that Chinese is a required locale for a region-specific use case. This can violate language or locale policy when users have not explicitly opted into Chinese-only interaction.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

L69-L78 将免费版基础设计域限定为 product/style/typography/color/ux 五个域，L224 也再次说明免费版仅有 5 个基础设计域。但 L132 的示例命令使用 --domain landing，这与前述支持范围直接冲突，会误导用户认为免费版包含额外域能力。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger section says to use the skill whenever there is a need for 'design creation, UI design, poster making, brand visuals,' which is a very broad activation scope. It does not clearly distinguish when this specific skill should activate versus other general design tools, and the inclusion of broad phrases increases the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

L196-L217 明确指导“在项目根目录创建 design-config.json 管理设计决策”，这属于将设计系统/设计决策持久化到文件。与此同时，L227、L283 分别声明免费版“设计系统持久化：不支持”和“免费版不支持设计系统持久化”，两者在意图层面直接矛盾。

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
88% confidence
Finding

The skill includes instructions to run privileged package-management commands with sudo. In an agent context with exec enabled, encouraging elevation increases the risk that users or agents execute system-modifying commands unnecessarily, expanding the blast radius if the environment or surrounding instructions are compromised.

Content

Scanner excerpt · SKILL.md (reported line 315)May include surrounding context.

md
brew install python3

# Ubuntu/Debian
sudo apt update && sudo apt install python3

# Windows
winget install Python.Python.3.12

Static analysis

No suspicious patterns detected.