Back to skill

Security audit

智能 UI 美化技能,支持30种设计风格(Notion/Figma/Linear/Apple 等),自动检测项目类型并生成实时预览

Security checks for vulnerabilities and agentic risk

Overview

This UI beautifier is purpose-aligned and shows no exfiltration or persistence, but its documented preview mode is not actually non-mutating and the script can overwrite project files without confirmation.

Review before installing if you care about preserving an existing project tree. Use a Git working tree or backup first, run --dry-run, and treat --preview as mutating until the skill is fixed. Pay special attention to existing DESIGN.md, styles/theme-override.css, assets/theme-override.css, and tailwind.config.js because they may be overwritten.

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
  • 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 (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill documentation is entirely in Chinese and the natural-language invocation guidance is presented only in Chinese, with no indication that users may choose another language. This creates a language/locale constraint that is not offered as an option or justified as region-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README advertises very broad natural-language triggers such as '帮我把语文网站改成 Notion 风格' without defining invocation boundaries, confirmation requirements, or scope constraints. In agent environments, vague trigger phrases can cause unintended activation or application to the wrong project/path, increasing the risk of unauthorized file modifications or misuse through prompt ambiguity.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file presents all user-facing instructions and warnings in Chinese, and there is no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific audience. This can violate language/locale policy when a skill implicitly forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This codebase is written to present its help text, UI labels, and generated HTML in Chinese, and the preview HTML explicitly sets lang="zh-CN". That imposes a specific language/locale on all users without offering a choice or documenting a region-specific requirement, which conflicts with the language/locale policy criteria.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The tool documents --preview as 'not modifying the original project', but it writes preview-<style>.html directly into the target project directory. This creates a mismatch between user expectation and actual behavior, which can lead to unintended repository changes, polluted working trees, or accidental inclusion of generated files in commits and deployments.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code creates and overwrites files such as DESIGN.md, styles/theme-override.css, tailwind.config.js, and assets/theme-override.css inside the user-supplied project path. Although the help text mentions preview and dry-run modes, there is no direct warning or confirmation before these project-modifying writes occur in normal execution.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The documentation presents dry-run as a mode to preview changes without applying them, but the script's compare and preview features can still trigger external side effects by launching the local browser via webbrowser.open. While this does not modify files, it goes beyond a purely passive preview and is not reflected in the documentation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.