Security audit
Security checks for vulnerabilities and agentic risk
This is a simple fact-checking guidance skill with broad but disclosed triggers and no hidden code, persistence, credential use, or destructive behavior.
Install this if you want the agent to be more deliberate about checking facts, numbers, code, and completed operations. Expect it may add extra verification steps or confidence labels in routine technical work; users who do not read Chinese may want a translated version of the instructions.
The description and operating instructions are written entirely in Chinese, and there is no indication that the user can choose another language or that the skill is intended only for a Chinese-language environment. This can violate language/locale policy when a skill implicitly enforces one language without opt-in.
The front-matter trigger conditions are broad enough to activate the skill after many ordinary assistant tasks, such as generating technical content or code examples. Over-broad invocation can cause unintended post-processing, user-confusing behavior, and expanded attack surface if adversarial content can intentionally trigger the skill in inappropriate contexts.
The trigger list in the body further broadens activation with ambiguous items like '生成技术内容后' and '完成外部操作后' without defining thresholds or scope. This can make the skill fire in routine interactions, causing unintended execution paths, wasted resources, and potential interference with other skills or workflows.
