Security audit
Security checks for vulnerabilities and agentic risk
This skill is a Chinese-language manufacturing handoff summarizer with a local Python helper; its main configured behavior is purpose-aligned and does not show hidden exfiltration, persistence, or destructive actions.
Install only if you want Chinese-language manufacturing shift handoff drafts and are comfortable providing local input files to a Python helper. Use explicit input and output paths, avoid pointing it at sensitive directories, and review generated handoff content before using it operationally because it is not a replacement for formal EHS records.
声明描述的是制造现场交接场景下的业务性整理工具，重点应围绕设备状态、异常、待办和安全提醒。实际代码并未体现任何制造、设备、班次、交接或 EHS 领域逻辑；它从 resources/spec.json 读取配置后，按 mode 运行多种通用审计功能，包括文本结构化摘要、目录扫描、CSV 审计、正则模式安全扫描以及 Skill 规范检查。这些能力与声明用途存在明显偏离，且包含未声明的代码/目录审计能力。因此属于描述与实际行为的实质性不匹配。
The script implements multiple generic auditing modes such as directory, CSV, pattern, and skill audits that are unrelated to manufacturing shift handoff summarization. This materially expands the skill’s capability to inspect arbitrary local files and repositories, increasing the risk of unintended data exposure and violating the principle of least functionality for the declared purpose.
Repository and code-auditing logic allows the skill to enumerate files, parse project metadata, and scan content patterns even though the skill is described as a production shift-handoff assistant. In this context, the mismatch is dangerous because it enables collection and summarization of unrelated local project information that operators would not expect this skill to access.
The entire skill description is written as a Chinese-only workflow for producing handoff summaries, and it does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without opt-in or documented justification is a natural-language policy concern.
The listed trigger examples, especially '把这班的情况整理成交接摘要' and '突出设备状态和异常', are phrased as general natural-language requests without clear routing constraints, exclusions, or invocation boundaries. In a chat or workplace-assistant context, these common phrasing patterns could cause unintended activation for routine summarization requests that are not meant for this specific skill.
The skill advertises executable capabilities via python3 and references local files/templates, but does not declare an explicit tool scope such as allowed tools or permissions. This creates an authorization ambiguity where an agent/runtime may permit broader shell or file operations than users expect, increasing the chance of unintended reads, writes, or command execution.
The documentation claims the skill is 'default read-only' and outputs only a handoff draft, yet it instructs use of python3 ... --output <输出文件>, which performs file creation or modification. This mismatch can mislead users and orchestrators about side effects, weakening trust boundaries and enabling unintended writes in environments that assume read-only behavior.
This markdown template forces a single language/locale for all users through its headings and instructions, but does not indicate that the skill is China-specific or that users can opt into Chinese output. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific.
The recursive file enumeration routine walks arbitrary user-supplied directories and collects many text-based files without any boundary checks. While not code execution by itself, this broad crawling can expose sensitive operational, credential, or internal documentation data and is not justified by the manufacturing handoff use case, making the context more suspicious.
The generated report strings are written in Chinese literals such as "结果", "摘要", and workflow guidance text, and the script does not provide any locale or language selection. This forces a specific language for all users and matches the policy category for language/locale violations.
This markdown example output forces a specific language/locale in its headings and content, and there is no indication that Chinese output is optional or limited to a region-specific use case. Under the policy, skills should not impose a language choice without user opt-in or clear justification.
No suspicious patterns detected.
