# OpenAI — Running Codex safely at OpenAI

- Company: OpenAI (openai.com)
- Announced: 2026-05-08T12:30:00+00:00
- Subject: GPT / ChatGPT / API
- Models affected: Codex
- Source: https://openai.com/index/running-codex-safely
- Record: https://forck.live/items/138-running-codex-safely-at-openai

OpenAI describes how it runs Codex securely using sandboxing, approvals, network policies, and agent-native telemetry.

## Evidence

Verbatim from https://openai.com/index/running-codex-safely:

> How OpenAI runs Codex securely with sandboxing, approvals, network policies, and agent-native telemetry to support safe and compliant coding agent adoption.

---

Record: https://forck.live/items/138-running-codex-safely-at-openai
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md