Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language decision-reasoning scaffold with broad auto-trigger wording, but it does not include code execution, credential access, persistence, or data exfiltration behavior.
Install this if you want Chinese-language structured decision analysis. Be aware that its auto-trigger keywords are broad and may make the agent use the framework in more conversations than intended.
The trigger list is extremely broad and includes common words like '分析', '如何', and '是否', making the skill likely to activate during ordinary conversation rather than only when explicitly requested. In an agent setting, this can cause prompt injection of the scaffold into unrelated tasks, change response behavior unexpectedly, and interfere with higher-priority safety or task-specific instructions.
The description claims the skill is suitable for nearly all decision scenarios without defining clear boundaries, encouraging indiscriminate use. In practice this increases the chance the skill will be applied in contexts where it is irrelevant, conflicts with domain-specific workflows, or amplifies the overbroad auto-trigger behavior.
The natural-language description, triggers, examples, and output template are entirely Chinese, and the file does not indicate that users may choose another language or that the Chinese-only behavior is an intentional, justified locale constraint. This can constitute a language/locale policy issue when a skill implicitly forces one language without user opt-in.
The package description in L04 is entirely in Chinese, which indicates a fixed language presentation. For an organizational language/locale policy check, this is a natural-language constraint without any opt-in, alternative locale, or justification that the skill is region-specific.
