Security audit
Security checks for vulnerabilities and agentic risk
This skill is a Chinese-language coding-guidelines checklist with no evidence of hidden data access, persistence, or unsafe execution.
Before installing, note that the skill may activate on fairly general Chinese phrases about behavior or programming standards, and its guidance/output is primarily Chinese. It does not appear to perform sensitive actions.
The trigger list includes generic phrases such as "行为规范", "编程规范", and "LLM陷阱" without context constraints or exclusion conditions. In a markdown skill description, these broad terms could match ordinary conversation about coding practices rather than an intentional request to invoke this specific skill.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
### 1. Think Before Coding（三思而后行）
> "The models make wrong assumptions on your behalf and just run along with them without checking."
**核心原则：**
- **不确定就先问，别猜。** 有歧义时呈现多个选项，而不是选一个闷头做。
This shell script's title, comments, and emitted checklist are predominantly in Chinese, with no indication that language is selectable or that the skill is intentionally limited to a Chinese-speaking context. Under the policy rule, a skill that imposes a specific language without user opt-in can constitute a locale/language policy violation.
No suspicious patterns detected.