Security audit
Security checks for vulnerabilities and agentic risk
This is a small Chinese-language coding helper skill with disclosed code-generation and execution guidance, and I found no hidden payloads, persistence, credential use, or exfiltration behavior.
Install this if you want a concise Chinese-language coding helper. Review generated scripts before running them, use a sandbox or virtual environment for unfamiliar code, back up data before file or database changes, and be careful with package installs, scraping, macros, and SQL UPDATE or DELETE statements.
The skill advertises Python script generation and execution but provides no warning about code execution, untrusted input, file access, dependency installation, or data exfiltration risks. In a coding assistant context, this omission is dangerous because users may treat generated or executed code as safe by default, leading to unsafe execution of harmful scripts or misuse of local data.
The README uses very broad natural-language trigger examples such as writing Python scripts, Excel formulas, mini-program pages, and SQL queries. In agent environments, such generic phrases can cause the skill to activate for many ordinary user requests, increasing the chance of unintended invocation and exposing users to risky capabilities like code generation or execution without clear consent boundaries.
L003 的自然语言描述完全以中文呈现，且文件中未说明是否支持按用户偏好切换语言，也未提供语言选择机制。根据规则，若技能在语言或地区上存在默认强制而无用户选择，属于自然语言策略违规风险。
L010 将触发场景定义为“当用户需要快速生成代码、自动化脚本、数据处理或查询时使用此技能”，覆盖面非常广，但没有列出明确触发短语、边界或排除条件。这样的描述容易让技能在大量普通编程相关对话中被误触发，属于模糊触发范围。
All user-facing instructions and examples in the file are Chinese-only, which can amount to an implicit language constraint without user opt-in. The document does not state that the skill is region-specific or offer alternative language support, so it may violate language/locale choice expectations.
No suspicious patterns detected.
