Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Chinese-language audit-preparation assistant that may create report files, with no evidence of hidden code, credential access, persistence, or exfiltration.
Before installing, note that this skill is written for Chinese-language audit preparation and may create multiple txt/md report files in the current working directory. Use it in an appropriate project folder and review generated audit content before sharing it.
The markdown explicitly lists trigger phrases such as “审核准备”, “迎检”, and especially “陪同”, which are broad terms that can arise in ordinary workplace conversation outside this skill’s intended scope. The file does not provide exclusion conditions or negative examples to clarify when these terms should not activate the skill.
The skill explicitly states it will write multiple txt/md files into the user's working directory, but there is no clear consent step or warning about filesystem modification. In agent environments, silent file creation can surprise users, overwrite existing files with date-based names, leak sensitive audit content into synced/shared directories, or be chained with broader tool access in unsafe ways.
The skill instructions, role description, workflow, and outputs are all specified in Chinese, which can effectively force a specific language experience if invoked by users with other language preferences. The file does not offer an opt-in language choice or justify that the skill is intentionally limited to a Chinese-language or region-specific audience.
