Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Chinese vocational-education document generator with local document-processing scripts and no evidence of hidden exfiltration, persistence, or destructive behavior.
Install only if you intend to process vocational-education documents locally. Review any automatically retrieved teaching-standard PDF source before allowing download, and expect the advertised built-in retrieval feature to be incomplete because referenced search/index assets are missing.
声明描述的核心能力是生成职业教育专业人才培养方案文档，且强调基于职业分析报告、专业教学标准、公共基础课列表进行整合，并输出 docx 文档。实际代码并未实现这些流程：它没有处理职业分析报告，没有应用专业教学标准规则库，没有生成 docx，也没有输出完整培养方案文本。代码的主要目的只是根据提供的课程分类数据生成一张课程体系架构 PNG 图片，属于辅助可视化产物，而不是所声明的主功能。因此这是明显的描述与行为不一致。
声明描述的是一个面向职业教育场景的内容生成技能，核心应包括专业分析、教学标准应用、课程体系/培养方案结构化生成等业务逻辑。实际代码却只是一个独立的 DOCX 后处理脚本，操作范围限于文档格式层面：表格边框、表头样式、字号、页边距等。虽然这类格式处理可能是生成 DOCX 的辅助步骤，但当前提供的代码片段本身并未实现声明中的核心功能，因此该描述与代码行为存在明显不匹配。
声明描述的是一个面向职业教育场景的高层业务技能，核心能力应包括解析职业分析报告、套用专业教学标准、整合课程与培养要求，并最终生成结构化的 docx 人才培养方案。而提供的代码块只是一个独立的预处理脚本，负责把多种文档格式转换为纯文本并保留表格结构，属于前置支持步骤。虽然声明中提到“预处理”是流程的一部分，但该代码没有体现所声明技能的主要功能，也没有任何职业教育领域特定逻辑、模板生成逻辑或 docx 输出逻辑。因此该代码块与声明的主要目的存在明显不匹配。
The skill declares file read/write capable behavior through its documented workflow, but it does not define an explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where a host agent may grant broader filesystem access than users expect, increasing the risk of unintended reads, writes, or overwrite of local files during document generation.
The top-level description defines a wide automatic-trigger surface without clear boundaries, making it easier for the skill to activate in contexts where the user did not intend a full pipeline involving retrieval, parsing, and document generation. In agent environments, ambiguous routing can become a security-relevant issue when it causes unnecessary data handling or network activity.
The trigger conditions are broad enough to match ordinary discussion of curriculum design or related education tasks, which can cause accidental invocation of a skill that reads files, downloads documents, and writes outputs. Overbroad auto-triggering increases the chance of unnecessary document processing and unintended access to user-provided materials.
The skill explicitly supports automatic download and parsing of external teaching-standard PDFs, but the workflow does not require clear user consent or provide strong controls around remote content retrieval. Remote file fetching expands the attack surface through malicious files, unexpected network destinations, tracking, and processing of untrusted content.
SQP-3 适用于所有文件类型。L655 规定“全程使用……规范术语”，结合全文中文指令语境，实际上将输出语言固定为中文，但未说明这是面向特定中文用户群的限定条件，也未给出用户语言偏好选择。若组织要求不强制特定语言/locale，则这属于语言策略约束不当。
The title and the entire instruction set are written as prescriptive rules in Chinese, and no part of the file offers an opt-in or alternative language/locale. Under the policy for natural-language violations, forcing a specific language without user choice is a reportable issue unless the locale restriction is explicitly justified.
The title and core instruction text are entirely in Chinese, and L003 states users 'must' follow this guide before continuing, with no indication that another language is available. This creates a natural-language locale constraint without user opt-in or a documented region-specific justification in the file.
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
| `Font not found` | 中文字体缺失 | Linux安装 `wqy-microhei` 或 `wqy-zenhei`；Windows使用 `msyh.ttc` |
| `PIL not installed` | Pillow库缺失 | `pip install Pillow==11.1.0` |
| `JSON parse error` | 传入数据格式错误 | 检查JSON字符串格式，确保课程列表为数组 |
| `Permission denied` | 输出目录无写权限 | `chmod 755 <output_dir>/images/` 或更改输出路径 |
---
Line L131 states that generated content should '优先使用以下规范化术语', imposing a fixed linguistic style in Chinese for outputs. This can be a language/locale policy issue because the file does not indicate any user opt-in, alternative language handling, or that the skill is explicitly limited to Chinese-language use.
Line L12 states that the language must be written vocational education terminology, effectively enforcing a specific language/locale style. Under the policy rule, forcing a language without user opt-in or a clearly documented justification is a natural-language policy concern.
The file title and mandatory instruction indicate the skill must load and follow this Chinese-language rules document, but there is no natural-language indication that users may choose another language or locale. Under the policy, forcing a specific language without opt-in or documented justification is a reportable locale/language constraint.
This Python file contains its module description, CLI help text, and output/status messages in Chinese only, which effectively forces a specific language for users. The file does not indicate that the skill is region-specific or provide any user opt-in or alternative locale support, matching the language/locale policy violation criteria.
This markdown file contains user-facing instructional content exclusively in Chinese from start to finish. Under the language/locale policy criterion, forcing a specific language without opt-in can be a natural-language policy concern when no alternative language option or explicit justification is provided in the file.
This markdown file presents all instructions and content exclusively in Chinese and does not indicate that users may choose another language or locale. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue unless the constraint is explicitly documented and justified.
This markdown file contains user-facing natural-language instructions exclusively in Chinese, and it does not indicate that the user can choose another language or that the skill is intentionally restricted to a Chinese-language context. Under the policy rule for language or locale constraints, forcing a specific language without opt-in is a reportable issue.
This Python file contains user-facing natural-language strings such as the module docstring, CLI description, and argument help text entirely in Chinese. Under the policy rule for language/locale, this is a violation because it imposes a specific language without any visible opt-in or indication that the tool is intentionally limited to a Chinese-speaking context.
The module docstring is written entirely in Chinese and establishes the script's user-facing description in a single language. Under the policy, forcing a specific language without opt-in or documented locale scope is a natural-language policy concern.
No suspicious patterns detected.