Source: Shell tool guide (OpenAI docs)

OpenAI's shell tool in hosted (managed Debian container, network off by default, org allowlist plus per-request network_policy, sidecar-injected domain secrets) and local modes.

Contents
  • What: official API documentation
  • Publisher: OpenAI
  • Date: living document, read 2026-11-14
  • Original: Shell tool

Summary

The Responses API shell tool runs commands either in OpenAI-hosted containers or in a runtime you host. The hosted mode is a general-purpose container (several languages, skills mounted as bundles) with explicit egress controls and secret substitution outside the model’s view.

Key claims

  • Hosted environments: container_auto (provisioned per request) or container_reference (a long-running container from the Containers API with a memory limit and inactivity expiry). Responses API only.
  • Image: Debian 12; working directory /mnt/data; no TTY, no sudo; Python 3.11, Node.js 22.16, Java 17, PHP 8.2, Ruby 3.1, Go 1.23 preinstalled.
  • Network: no outbound access by default. Enabling it takes an org-level admin allowlist plus a request-level network_policy that can only narrow it; requests naming other domains fail.
  • domain_secrets bind a named secret to an allowed domain; the model sees only a placeholder such as $API_KEY and a sidecar substitutes the real value for approved destinations only.
  • Skills are versioned bundles mounted into the container.
  • Local mode returns shell_call items for your own executor (replaces the retired local_shell tool); OpenAI recommends command allowlists, approvals for destructive actions, sandboxing with limits, own timeouts and full logging.
  • Network-fetched content may carry prompt injection; review logs of requested and actual destinations.

Feeds

Suggest changes →