# What your agent sandbox can reach by default

DevFeed: [What your agent sandbox can reach by default](<https://devfeed.tech/articles/what-your-agent-sandbox-can-reach-by-default-26791.md>)

Original publisher: [Read original article](<https://workos.com/blog/agent-sandbox-egress-defaults>)

Author: WorkOS

Published: 2026-09-15T00:00:00Z

Content type: article

Language: en

Sources: [WorkOS Blog](<https://devfeed.tech/sources/workos-blog.md>)

Topics: [Network](<https://devfeed.tech/topics/network.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [llms](<https://devfeed.tech/tags/llms.md>), [network](<https://devfeed.tech/tags/network.md>), [security](<https://devfeed.tech/tags/security.md>)

## AI overview

This reference compares outbound network access defaults in Codex, ChatGPT Work, Claude Code, and other hosted agent environments. It examines what the documentation says before configuration and argues that egress allowlists provide a stronger boundary than detection filters.

## Source excerpt

Codex, ChatGPT Work and Claude Code make five different choices about outbound network access. Here is what each one allows before you configure anything, what the docs publish, and where the boundary does not reach.