OpenAI
policyactive

Codex: Agent approvals and security

OpenAI

View original resource

OpenAI developer documentation for Codex agent approval modes (auto, read-only, full auto) and security settings, covering sandboxing, network egress controls, secret handling, and configuring approval prompts for tool execution in coding workflows.

Tags

agentic AIvendor-guidance

At a glance

Published

2026

Jurisdiction

Global

Category

Vendor guidance

Access

Public access

Build your AI governance program

VerifyWise helps you implement AI governance frameworks, track compliance, and manage risk across your AI systems.

Codex: Agent approvals and security | VerifyWise AI Governance Library