ClawHub
Back to skill

Security audit

笔记手账

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese educational prompt-template skill, with no executable code, network behavior, persistence, credential access, or hidden high-impact actions found.

Installers should expect this skill to generate Chinese-first educational image prompts and to activate on several broad visual-style keywords. It appears low-risk from a security standpoint because it ships only Markdown guidance and does not request credentials, run code, fetch remote content, or persist changes.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad terms such as general style/theme interests and popular culture keywords, which can cause the skill to activate in contexts unrelated to the user’s intent. This increases the chance of unintended invocation, prompt hijacking of normal conversations, and confusing or irrelevant behavior, especially because the list mixes niche skill names with common descriptive words.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file consistently specifies Chinese titles, labels, handwritten text, and Chinese font styling throughout the example prompts, effectively constraining the skill's output language to Chinese. There is no indication that this is optional, user-selected, or justified as a region-specific tool, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L125 states "语言 | 默认中文", which imposes a language default in natural-language guidance. The policy requires flagging language or locale constraints when the skill forces a specific language without explicit user opt-in or offering a choice.

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 is written as normative style guidance for prompt generation and presentation, and it frames the skill as a Chinese note/handbook style system without any indication that language or locale is optional. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · styles.md (reported line 7)May include surrounding context.

md
## 视觉DNA

| 元素     | 特征                                                                                                                  |
| -------- | --------------------------------------------------------------------------------------------------------------------- |
| **基底** | 暖奶油色纸张底纹，轻微纤维纹理，撕纸毛边，活页孔，螺旋装订                                                           |
| **风格** | 墨蓝手账风格（默认）：墨蓝主调，暖金点睛，优雅规整，文气从容。另有经典/活力手账/科幻/青绿新生/蔚蓝格调/二次元/动漫/少女粉/我的世界像素风 |

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · styles.md (reported line 202)May include surrounding context.

md
## 内容模块

| 模块           | 用途       | 样式                                                                                    |
| -------------- | ---------- | --------------------------------------------------------------------------------------- |
| **标题区**     | 主题名称   | 风格对应字体加粗 + 主题色手绘色块/波浪下划线，醒目吸睛                                  |
| **分区卡片**   | 知识点讲解 | 白色/浅色卡片 + 主题色顶部条/角标 + 错落编号标签                                        |

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document title and throughout the templates prescribe Chinese-language output elements such as headings and labels, while the file does not state that language selection is optional or user-configurable. This can violate a language/locale policy when a skill imposes one language by default without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file title and explanatory text are entirely in Chinese and present the changelog as part of the skill's maintained documentation, which suggests a fixed language expectation. Under the policy criteria, forcing a specific language without user opt-in can be a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The principle “中文优先｜所有文字内容默认中文” establishes a language default that can override user locale preference, and the file does not mention offering alternative languages on request. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.