Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward code-review skill that reads requested code or diffs and produces a structured review report, with no hidden execution, persistence, or data-exfiltration behavior found.
Install this if you want a Chinese-language structured code review workflow. When invoked, expect it to inspect the code, commit, or pull request diff you ask it to review; avoid pointing it at repositories or diffs containing sensitive material unless you are comfortable with that content being processed by your agent.
The skill metadata and body are written as an instruction set in Chinese and direct the review workflow and report structure in that language, but there is no opt-in or note that the skill can adapt to the user's preferred language. This creates a language-policy concern because the skill appears to impose a specific locale by default.
The trigger condition is broad enough to activate on many ordinary requests for code help, which can cause the skill to take over interactions outside its intended scope. In practice, this increases the chance of inappropriate tool use such as fetching diffs or repository content when the user only wanted lightweight advice, creating unnecessary exposure of code or context.
No suspicious patterns detected.
