Security audit
Security checks for vulnerabilities and agentic risk
This is a simple local meeting-minutes extractor whose documentation overpromises missing push and todo features, but the inspected files do not show hidden, destructive, persistent, or exfiltration behavior.
Install this only if you want a local Chinese-language helper for turning existing text notes into a simple minutes document. Do not rely on the advertised todo extraction or enterprise chat push commands unless those missing scripts are supplied and reviewed separately. Meeting notes can be sensitive, so keep outputs in an intended workspace path and review content before sharing it elsewhere.
代码的核心行为与“会议纪要整理”总体方向一致：它读取输入文件、识别讨论/决议/待办相关段落并输出结构化纪要，因此与声明中的会议纪要整理、待办提取部分是相符的。但声明中明确提到支持多渠道推送到企业微信/飞书/钉钉，代码中完全没有任何网络请求、API调用或推送实现；同时也没有录音、转写或实时记录会议的功能，只能处理现成文本。所谓关键讨论点/会议摘要也只是通过简单关键词切换段落收集内容，并非真正的摘要提取。因此该描述相对代码能力存在明显夸大，属于描述与实际行为不完全一致。
The skill advertises and demonstrates commands that write output files, but it does not declare any explicit tool scope or permissions boundaries. In an agent setting, undocumented file-write capability can lead to unintended overwrites, creation of sensitive artifacts, or execution beyond what reviewers and users expect.
Meeting minutes commonly contain confidential business discussions, personnel information, action items, and internal decisions. Advertising pushes to external enterprise channels without any privacy warning, consent checkpoint, or data-sharing explanation increases the risk of accidental disclosure of sensitive information to third-party systems or unintended recipients.
The file’s title, section headers, fallback text, and argument help strings are all hard-coded in Chinese, and the extractor emits Chinese-formatted meeting minutes regardless of user preference. This creates a language/locale policy issue because the skill does not provide any opt-in, configuration, or justification for restricting output to a specific language.
The natural-language description and usage guidance are entirely in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the stated policy, forcing a specific language without user opt-in can be a locale-policy issue.
No suspicious patterns detected.
