CRITICAL9.8

GHSA-xrxf-jgv3-qmrm

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

Details

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.

Are you affected?

Enter the version of the package you're using.

Affected packages

npm/@openai/codex

Introduced in: 0

No fixed version published yet for @openai/codex (npm). Pin to a known-safe version or switch to an alternative.

References

https://nvd.nist.gov/vuln/detail/CVE-2025-61260[ADVISORY]
https://github.com/openai/codex[PACKAGE]
https://research.checkpoint.com/2025/openai-codex-cli-command-injection-vulnerability[WEB]
http://openai.com[WEB]