Back to skill

Security audit

Material Design Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Material Design reference skill with some routing and language-quality caveats but no evidence of hidden execution, data theft, persistence, or destructive behavior.

Before installing, consider narrowing activation if you work on non-Material UI topics, and verify code examples against current official Material/Flutter/Android docs before copying them into production. The skill appears safe as a reference package but may be opinionated and Chinese-first in its responses.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (22)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · references/motion.md (reported line 321)May include surrounding context.

Android uses the Transition framework with spring physics.

xml
<!-- res/anim/fragment_fade_through.xml -->
<transitionSet xmlns:android="http://schemas.android.com/apk/res/android"
    android:transitionOrdering="together">
    <fade android:fadingMode="fade_out" />

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger terms are broad design-related keywords such as '设计系统' and 'Android UI', which can cause the skill to activate in many unrelated conversations. Over-broad activation can inject irrelevant guidance, crowd out more appropriate skills, and increase the chance that users receive unintended recommendations in contexts the author did not anticipate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description and content are written as a Chinese-only operating mode, and the output guidance also prescribes a fixed response style without indicating that language should follow user preference. This can violate language/locale policy when a skill implicitly forces one language without opt-in or clear region-specific justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says the skill triggers when the user "mentions" a wide set of terms, but it does not define whether simple keyword presence is sufficient or whether user intent must be about Material Design. Ambiguous mention-based activation creates routing uncertainty and can lead to false positives where the skill is invoked for incidental references, reducing reliability and potentially suppressing safer or more relevant skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger regex is extremely broad and includes generic terms such as "Compose", "Typography", "配色方案", "按钮样式", and "输入框" that commonly appear in unrelated UI, frontend, and design discussions. This can cause unintended activation of the skill, overriding more appropriate routing and increasing the chance that the model injects irrelevant or stale guidance into unrelated conversations.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/color-scheme-roles.md (reported line 291)May include surrounding context.

md
## 相关链接

- [Material 3 迁移指南](https://flutter.cn/ui/design/material)
- [ColorScheme.fromSeed API](https://api.flutter.cn/flutter/material/ColorScheme/fromSeed.html)
- [Material Color Utilities 包](https://pub.dev/packages/material_color_utilities)
- [Flutter Material 3 Demo](https://github.com/flutter/samples/tree/main/material_3_demo)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/m3-migration-guide.md (reported line 518)May include surrounding context.

md
## 相关链接

- [Material 3 迁移指南](https://flutter.cn/ui/design/material)
- [ColorScheme.fromSeed API](https://api.flutter.cn/flutter/material/ColorScheme/fromSeed.html)
- [Material Color Utilities 包](https://pub.dev/packages/material_color_utilities)
- [Flutter Material 3 Demo](https://github.com/flutter/samples/tree/main/material_3_demo)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file includes a Chinese-only description string in the front matter while the rest of the document is in English, and there is no indication that users can choose their preferred language. Under the policy rule for natural-language violations, forcing a specific language without opt-in is reportable unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

该 markdown 文件从标题开始即以中文撰写,且全文未说明这是面向中文用户的区域性文档,也未提供语言选择或用户自选语言的说明。根据规则,强制特定语言而无用户选择或明确合理说明,属于自然语言层面的语言/区域策略违规。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description is written entirely in Chinese, which indicates a fixed language/locale choice in the skill content. Under the policy, language constraints should be opt-in or clearly justified as region-specific; no such choice or justification appears here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description is written entirely in Chinese while the rest of the document is primarily in English, which creates an implicit language constraint without user opt-in. Under the language/locale policy, forcing a specific language is a violation unless the skill clearly offers a language choice or is explicitly documented as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The README is entirely written in Chinese and does not state that language selection is optional or limited to a justified region-specific audience. Under the policy, forcing a specific language without user opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

At L140-L147, the document explains that MD3 replaced the old surfaceTint overlay model with tone-based surface colors for elevation. However, the code comment at L162 says 'MD3 中 Card 的 elevation 现在用 surfaceTint 实现', which directly contradicts that stated model and could mislead readers about how elevation coloring works.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is written entirely in Chinese and does not indicate that alternative languages are available or that the skill is intentionally limited to Chinese users. This can violate language/locale policy expectations when a skill implicitly constrains output or audience language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown reference forces a single language/locale for all instructions and labels, and there is no indication that the user can opt into another language. Under the policy, language-specific content should either offer choice or clearly justify the locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file is entirely presented in Chinese and labels the source as a Chinese Flutter site, with no indication that language selection is optional or that the locale is intentionally constrained for a specific audience. Under the stated policy, 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
89% confidence
Finding

The entire skill document is written in Chinese and does not indicate that users may choose another language or that the content is intentionally limited to a Chinese-speaking audience. Under the policy, a fixed language without user opt-in can be a natural-language locale violation unless the regional constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file presents all instructional content in Chinese and does not indicate that users can select another language or that the skill is intentionally restricted to a Chinese-speaking audience. That can violate a language/locale policy when skills are expected to avoid forcing a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The comment says the snippet is for '尊重减少动画' and the next line claims to use programming-based system-setting detection, but the code shown instantiates rememberInfiniteTransition, which represents ongoing animation rather than reduced-motion handling or preference detection. This is an intent-level contradiction in the inline documentation, not merely an incomplete example.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The Compose example passes a fixed locale string, "en", when constructing the color scheme. This is a natural-language locale constraint presented without opt-in or explanation, which can violate language/locale policy expectations for user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description is written entirely in Chinese ('完整参考'), and the rest of the file likewise presents the reference content in Chinese without indicating that language selection is optional. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is reportable even in documentation files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file is primarily written in English, but the manifest description at L003 is Chinese-only. Because the file does not indicate that the skill is intended specifically for Chinese-speaking users or provide any language/locale opt-in, it can violate the policy against forcing a specific language without user choice.

Content

No source excerpt is available for this finding.