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 Protocol) configuration files. The attack …
Published: 2026-04-14 · CVSS: 9.8 · CVSS 3.1
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.
Source: CVE Program · Revision 8b16575c39f1e1810c5e863010da073d2d3285e7