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.
{
"cwe_ids": [
"CWE-94"
],
"github_reviewed": true,
"github_reviewed_at": "2026-04-16T22:56:42Z",
"nvd_published_at": "2026-04-14T15:16:24Z",
"severity": "CRITICAL"
}