GitStock

openai/codex · Security

OpenAI Codex CLI enables code execution through malicious MCP (Model Context Protocol) configuration files

Open GitHub
GHSA ID
GHSA-xrxf-jgv3-qmrm
CVE ID
CVE-2025-61260
Severity
critical
Published
Updated
CVSS
9.8 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CVSS v3
9.8 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Description

A vulnerability was identified in OpenAI Codex CLI v0.23.0 and before that enables code execution through malicious MCP (Model Context Protocol) configuration files. The attack is triggered when a user runs the codex command inside a malicious or compromised repository. Codex automatically loads project-local .env and .codex/config.toml files without requiring user confirmation, allowing attackers to embed arbitrary commands that execute immediately.

CWEs

  • CWE-94 · Improper Control of Generation of Code ('Code Injection')

References