Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese knowledge-card generation skill with local rendering scripts; it has quality and local HTML-sanitization issues, but I found no hidden credential access, persistence, exfiltration, or destructive behavior.
Install this only if you want a Chinese-language Xiaolvshu/WeChat-style card workflow. Expect it to create local HTML, TXT, and PNG outputs under the OpenClaw workspace and to rely on local Chrome or Playwright for screenshots. Do not put secrets or untrusted HTML/JavaScript into the topic or card text unless the generator is updated to escape user input.
声明描述的是一个通用、面向多场景的知识卡片设计技能，强调内容创作与设计方法论；但代码实际仅执行固定模板文件的本地渲染与截图，且主题限定为“GTC 2026 产业趋势卡片”。这不是单纯的实现细节差异，而是主要目的和能力范围上的偏差。虽然两者都与“卡片生成”有关，但代码并未体现声明中的通用知识卡片生成、读书笔记/书籍分享场景适配或设计原则应用能力，因此应判定为描述与行为不一致。
The code is related to the declared domain of Xiaolvshu-style knowledge cards, so it is not unrelated or malicious. However, the description overstates the functionality. The script does not actually generate polished final cards or PNG outputs; instead it creates basic HTML templates and a TXT draft with many '待填写' placeholders. It also does not contain substantive logic demonstrating CRAP-principle layout reasoning or color psychology beyond selecting hardcoded color palettes. Thus the declared description is only partially accurate and materially exaggerates the implemented capability.
The skill advertises file-writing and shell-like operational capabilities through referenced scripts and generation/export workflow, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates an unsafe trust boundary: an agent may infer broader execution rights than intended and perform filesystem or command execution actions without least-privilege constraints.
The description is written as a prescriptive Chinese-only capability ('生成小绿书风格知识卡片的专家技能') and the file provides all instructions, examples, and outputs exclusively in Chinese with no opt-in or alternative language handling. This creates a natural-language locale policy issue because the skill appears to impose a specific language experience rather than offering a user choice or documenting that it is intentionally region-specific.
The skill scope expands from visual design into recommendation-algorithm gaming and engagement optimization guidance, including formulaic interaction hooks and traffic-distribution tactics. This broadening can cause agents to generate manipulative growth content outside the declared design-only purpose, increasing the risk of policy evasion, spammy output, or platform-abuse assistance.
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
]
try:
subprocess.run(cmd, check=True, capture_output=True, timeout=30)
# 使用PIL裁剪到精确尺寸
img = Image.open(temp_file)
This code file includes its primary description, usage instructions, and generated user-facing guidance entirely in Chinese. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative language option or justification is provided.
User-controlled topic text is inserted directly into generated HTML and TXT without escaping or validation. In this skill context, that can turn untrusted input into active HTML/JavaScript when the generated preview pages are opened locally, and it also persists any sensitive text a user may accidentally include into output artifacts stored under the workspace.
Earlier documentation states the cover output size is 900×383px for 微信读书首页展示, but later sections require a 竖版3:4 cover at 1080×1440px as a must-follow formula and checklist item. This is an active contradiction in the skill's own documentation about what cover format should be generated.
The document declares lang="zh-CN", and the visible UI text throughout the template is also fixed in Chinese. This creates a language/locale constraint without any indication of user opt-in or a documented region-specific reason, which matches the policy-violation category for forced language or locale.
The document sets lang="zh-CN", which hard-codes a specific language/locale. Under the policy, locale-specific behavior should offer user choice or clearly document why the restriction is necessary; this standalone template provides neither.
The document declares lang="zh-CN", which hard-codes a specific language/locale in a user-facing template. Under the policy, locale constraints should either offer user opt-in/choice or be clearly documented as justified for a region-specific use case.
The document declares lang="zh-CN", which hard-codes a specific language/locale for the skill content. Under the policy, locale constraints should either be optional for the user or clearly justified as region-specific; this file provides neither.
The document declares lang="zh-CN", which fixes the content to a specific language/locale. Under the policy, locale-specific behavior should either provide user opt-in/choice or clearly document why the restriction is necessary; this file contains no such indication.
The document declares lang="zh-CN", which hard-codes a specific language/locale. Under the policy criteria, locale restrictions should either be optional for the user or clearly justified as region-specific; no such opt-in or justification appears in this file.
The document declares lang="zh-CN", which hard-codes a specific language/locale. Under the policy, locale constraints should either offer user choice or be clearly documented as justified for a region-specific use case, and no such opt-in or justification appears in this file.
The document declares lang="zh-CN", which fixes the content locale to Simplified Chinese. Under the policy, locale-specific behavior should either provide user choice or clearly justify the restriction; this file does neither.
The document declares lang="zh-CN", and all visible user-facing content is written in Chinese, which indicates a fixed language choice. Under the policy, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy concern.
The document declares lang="zh-CN", which fixes the content to a specific language/locale. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative or justification is provided in the file.
This markdown file presents all guidance in a single language and does not indicate that the user can choose another language or that the content is intentionally restricted to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all instructions and examples exclusively in Chinese, with no indication that users may choose another language or that the skill is region-specific.
The entire document is written in Chinese and presents the guidance as a universal design reference without any indication that language selection is optional or that the skill is intended only for Chinese-speaking users. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation.
The entire skill file is written as a Chinese-only visual system specification, including headings, labels, and usage guidance, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-language workflow. Under the policy rule, a fixed language without user opt-in can be a natural-language policy violation.
This markdown file is entirely written in Chinese and does not indicate that the user can choose another language or that the content is intentionally limited to a Chinese-only audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
SQP-3 applies to all file types and includes language or locale policy violations. This file presents all instructions in Chinese and does not provide any user opt-in, alternative language, or justification for a Chinese-only audience, which may conflict with a policy requiring language choice.
No suspicious patterns detected.