Back to skill

Security audit

UXD Design Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language UX design learning aid with local templates and simple generators, and I found no hidden persistence, credential access, network execution, or destructive behavior.

Installers should understand this is primarily a Chinese-language UXD/UXDA learning package. The helper scripts run locally and can save generated Markdown/CSV text to a path you provide; review the output path before using `--output`. I found no evidence of hidden data collection, remote payloads, or privileged behavior.

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
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (10)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

声明描述的核心能力是UXD流程学习与设计方法指导,覆盖研究、分析、原型、测试和报告框架等设计流程辅助场景。实际代码并未实现这些交互式设计流程指导能力,而是专注于为“UXD作品展示”生成视频讲解分镜脚本。虽然主体镜头中使用了“用户研究、洞察分析、设计原型、测试验证”等UXD阶段术语,但这些只是填充到视频脚本模板中的内容标签,并不提供相应的方法指导、分析辅助或流程决策支持。因此,代码的主要目的与声明用途存在实质性偏差,属于描述与行为不匹配。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill README presents the skill identity and usage entirely in Chinese from the title onward, with no indication that users may interact in other languages or select a preferred locale. Under the policy rule, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This is a code file, so SQP-3 applies to natural-language strings embedded in the script. The title, usage text, argument descriptions, error messages, and generated report content are all hard-coded in Chinese, with no opt-in or alternate locale, which constitutes a language/locale policy violation under the rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s title, usage text, CLI descriptions, and generated interview outline are written entirely in Chinese, and the skill does not indicate that language is configurable or optional. This creates a locale/language policy issue because the skill effectively mandates one language without user opt-in or a documented region-specific justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This file contains natural-language content entirely in Chinese, including usage instructions and UI labels, but does not offer any language option or document a region-specific reason for the locale restriction. Under the policy rule for language or locale constraints, this is a natural-language policy issue because it implicitly fixes the skill artifact to a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file contains user-facing instructions exclusively in Chinese, and there is no indication that users may choose another language or that the template is intentionally limited to a Chinese-speaking audience. Under the policy rule for language or locale constraints, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

该文件的标题、正文和示例全部以中文呈现,没有提供用户可选择其他语言的说明,也未标注这是面向特定中文用户群体的受限文档。按规则,未获用户选择或缺乏合理说明的固定语言/locale 约束属于自然语言政策风险。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The module is documented and implemented as a '视频脚本生成器' for producing presentation video storyboard scripts, including shot planning, narration, and production checklists. The manifest describes the skill as focused on UX design process guidance, research, competitor analysis, prototyping, testing, and report/framework assistance; audiovisual production scripting is adjacent but not clearly within that declared scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code's natural-language interface and generated output are written in Chinese, including the module description, CLI help, warnings, and narration guidance. The file does not indicate that language choice is optional or region-specific, so it may violate a policy requiring user opt-in before enforcing a specific language/locale.

Content

No source excerpt is available for this finding.