Running Codex safely at OpenAI
中文摘要
OpenAI 通过沙箱、审批、网络策略及遥测技术确保 Codex 安全，以支持安全合规的编程智能体应用。
English Summary
OpenAI secures Codex using sandboxing, approvals, network policies, and telemetry to ensure safe and compliant coding agent adoption.
原文节选
How OpenAI runs Codex securely with sandboxing, approvals, network policies, and agent-native telemetry to support safe and compliant coding agent adoption.