Inside the Codex sandbox

According to the description, OpenAI explains how its Codex coding agent runs commands on a user's machine while enforcing filesystem and network limits that the user controls, across macOS, Linux and Windows.

Why it matters

The same thing, for different readers.

What it means for you

OpenAI says its Codex agent can only touch the files and network access a user allows.

For researchers

OpenAI documents its sandbox design for coding agents, relevant to how agents are kept within bounds.

The record

Questions
Are AI companies putting stronger safeguards into practice? · Can AI systems act beyond what people intended or allowed?
What we read
We have read only the description the publisher gives. No quotations until someone reads the source itself.
Found by
The Radar, run of November 19, 2026, via openai-news (tier 1: the source’s own channel or an official record)
Cite this
OpenAI, “Inside the Codex sandbox”, November 18, 2026. Entry in the Ctrl AI Base, https://ctrlai.com/base/openai-2026-11-18-inside-codex-sandbox
Our notesLight lane: only the triage excerpt was read; whether the sandbox works as described is not tested here.