Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language workflow-planning skill with broad activation wording but no code, hidden execution, credential use, persistence, or data exfiltration behavior.
Install only if you want a Chinese workflow-design aid that may activate broadly; consider narrowing its description before publishing or using it in a mixed-language or task-specific environment.
The skill description states it should be used 'when we want to do anything,' which creates an extremely broad activation scope with no meaningful trigger boundaries. This can cause the agent to apply the skill to unrelated tasks, override more appropriate task-specific behavior, and expand the influence of any unsafe or low-quality instructions contained in linked resources.
The skill name and description are written entirely in Chinese and provide no indication that users may choose another language or locale. This can violate language/locale policy when the skill effectively assumes a single language without documenting opt-in or offering alternatives.
该技能文件全文以中文撰写，未见任何说明表示这是可选语言、面向特定中文用户群体，或提供其他语言/本地化选择。根据规则，若技能在自然语言层面强制特定语言且无用户选择或合理限定，属于语言/locale policy violation。
No suspicious patterns detected.
