Hi! Recapping some changes we have rolled out over the last couple of weeks that have further reduced the risk associated to potentially destructive actions being performed by Codex during its work. A few weeks ago, w…

OpenAI 针对 Codex 中 GPT-5.6 在极少数情况下执行破坏性命令的问题,发布了多项安全修复。这次更新重点解决了模型误删用户文件的风险,并强化了对高风险指令的拦截与审批机制。








