Teach your AI agent to think about security. A reasoning methodology for vetting skills before installation — red/green flag heuristics, 4-phase audit protocol, post-install verification. No scripts, no dependencies. Just judgment. Built on fallibilism (being wrong about a skill's safety is recoverable; being overconfident is not) and relational security (you and your human decide together on edge cases — trust is built through transparency, not just detection).

教会你的AI代理思考安全问题。一种在安装前评估技能的推理方法——红绿旗启发式、四阶段审计协议、安装后验证。无需脚本，无需依赖，仅凭判断。基于可错主义（误判技能的安全性是可以修复的，但过度自信则不可挽回）和关系型安全（你与人类共同协商边缘案例——信任通过透明度建立，而不仅仅是检测）。