Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language workflow checklist for iterative task completion, with no executable code, hidden data access, or persistence.
Install this if you want a Chinese iterative checklist for complex work. Review any suggested validation command before running it, especially commands that inspect your local skill list or project files, but the artifact itself does not show hidden access or unsafe persistence.
The manifest description and invocation guidance are written entirely in Chinese and present the interaction pattern in that language without any opt-in, alternative locale, or statement that the skill is intended only for Chinese-speaking users. Under the policy, forcing a specific language without user choice is a natural-language policy concern.
The file lists specific trigger phrases, but it also allows activation when 'complex tasks need multiple rounds of improvement' or when creating 'Skill/code tasks that need repeated checking.' These conditions are subjective and broad, making it unclear when the skill should activate versus when normal task handling should apply.
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
### 交付物
- [ ] 产出：SKILL.md 文件
- [ ] 路径：skills/xxx/SKILL.md
### 质量标准
- [ ] name 字段非空
No suspicious patterns detected.