ClawHub
Back to skill

Security audit

Ui Ux Promax V2 Free

Security checks for vulnerabilities and agentic risk

Overview

The skill presents as a UI/UX design helper, but it requests command execution and includes system-level install commands while the advertised local search tool is not included in the package.

Install only if you are comfortable reviewing commands before execution. Do not let an agent run the sudo, brew, winget, or troubleshooting commands automatically, and confirm whether the missing scripts/search.py and data files are supplied elsewhere before relying on the skill.

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 (5)

Chaining Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

The chained command 'sudo apt update && sudo apt install python3' encourages immediate privileged execution of multiple operations in one step, reducing opportunities for review and increasing the risk of unintended system modification. In the context of an exec-capable skill, command chaining makes automated or semi-automated execution more dangerous because validation of each step is bypassed.

Content

Scanner excerpt · SKILL.md (reported line 338)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
90% confidence
Finding

描述与全文均固定为中文表述，且未说明这是面向特定中文地区用户的受限技能，也未提供语言/locale 选择机制。按照语言/locale政策，技能不应在无用户选择或明确合理说明的情况下隐含强制单一语言。

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

L105 明确写明该能力“支持创建/查询/导出操作”，但同一文件后文说明免费版“设计系统持久化不支持”(L241、L310)且整体定位为快速查询型本地设计指南工具。这里不是单纯信息不完整，而是文档内部对该技能是否具备输出持久化/导出能力出现了直接矛盾。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

该行将技能触发描述为“需要设计创作、UI设计、海报制作、品牌视觉时使用”，范围覆盖非常广泛的常见设计需求，但没有给出明确触发短语、边界条件或排除示例。这样的描述容易让代理在大量普通设计相关对话中误判应自动调用该技能。

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
90% confidence
Finding

The skill includes privileged installation commands using sudo, which can lead an agent or user to perform system-level changes outside the core UI/UX design task. In a skill with allowed-tools including exec, embedding root-level package installation guidance increases the chance of unnecessary privileged execution and expands blast radius if the instructions are followed automatically or incautiously.

Content

Scanner excerpt · SKILL.md (reported line 338)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.