Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only backend API design skill whose repository-reading guidance is aligned with analyzing user-provided projects.
Install this if you want Chinese-language backend architecture and API design help. Provide only project paths you intend the agent to inspect, since the engineering-analysis mode tells the agent to read source files such as proto, SQL, Go, and service code.
The trigger list contains very broad phrases such as '业务方案', '架构设计', '需求分析', and '流程图', which are common in ordinary software conversations and can cause the skill to activate unintentionally. Unintended activation can expose repository structure, influence agent behavior outside the user's precise intent, or cause the skill to overtake more appropriate workflows.
The skill metadata and instructions are entirely written in Chinese and present the skill as operating in that language, but there is no indication that the user can choose another language or that the locale restriction is intentional and justified. This can violate language/locale policy when users have not opted into Chinese output.
The file title and all instructional content are written in Chinese, and the document does not indicate that this language choice is optional or limited to a China-specific audience. Under the policy scope provided, a skill that imposes a specific language without user opt-in can be a natural-language policy violation.
This markdown file is written entirely in Chinese, including headings, labels, and examples, with no indication that language selection is optional or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy rule for natural-language locale constraints, this can be considered a language policy violation because it imposes a specific language without user opt-in.
This markdown file is natural-language documentation and all headings, comments, and descriptions are presented in Chinese. Under the policy rule for language/locale, forcing a single language without user opt-in or explicit justification can be a policy violation.
No suspicious patterns detected.
