Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only AI coding workflow skill with some opinionated defaults, but no hidden execution, persistence, or data access behavior.
Install only if you want a Chinese-language, opinionated AI development workflow. Before using it for a real project, confirm the desired language, client/server stack, database, and security requirements so the generated code does not default to an unsuitable architecture.
The skill metadata and description are written only in Chinese, which implicitly constrains interaction to a specific locale without clearly offering a user-selected language option. This can cause the agent to respond in an unexpected language, reducing user control and increasing the chance that requirements, security constraints, or generated code details are misunderstood.
The embedded architecture prompt hard-codes Kotlin as the unified programming language for client and server without user opt-in, which can override user intent and push generation toward an unsuitable stack. In a code-generation skill, this matters because hidden stack constraints can lead to insecure or incompatible outputs if the user's environment, policies, or review processes expect a different language.
Line L38 explicitly requires the stack to '统一使用{Kotlin}语言'. In a natural-language policy sense, this forces a specific language choice rather than offering user selection or framing it as an optional example, and the document does not present an opt-in or alternative-language path.
No suspicious patterns detected.
