GitHub Advisoryadvisory · npm

GHSA-xrxf-jgv3-qmrm OpenAI Codex CLI enables code execution through malicious MCP (Model Context Protocol) configuration files

CRITICAL Published 2026-04-14 Modified 2026-04-16 Official page ↗
Aliases
CVE-2025-61260
Ecosystem
npm
Packages
@openai/codex
Severity
Critical
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weaknesses
CWE-94
Reviewed
2026-04-16

Affected packages

• npm @openai/codex: <= 0.23.0 (no fix yet)

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.

Related

Alias · CVE (1)

  • CVE-2025-61260 A vulnerability was identified in OpenAI Codex CLI v0.23.0 and before that enables code execution through malicious MCP (Model Context… vulnerability

Weakness · CWE (1)

  • CWE-94 Improper Control of Generation of Code weakness

References