Security audit
Security checks for vulnerabilities and agentic risk
This is a simple Claude prompt-writing guide with no code or privileged behavior; the only notable issue is Chinese-language examples that may influence response language.
Installers should expect a Chinese-language prompt-engineering helper. If they want language to follow each user request, they may want the examples clarified, but the package does not contain code, persistence, privileged access, or data-handling behavior.
The sample system prompt explicitly says '使用中文回复', which imposes a specific language on outputs. The file does not indicate that this is optional or based on user preference, so it conflicts with the policy against forcing a language or locale without opt-in.
The output-control section includes '指定语言："用中文回复"' as guidance, but does not clarify that language should be chosen based on user preference. This can be read as endorsing a fixed-language behavior without opt-in.
No suspicious patterns detected.
