Affected Vendor(s)
Affected Product(s)
Summary
A critical vulnerability exists in OpenAI Codex CLI that allows arbitrary command execution when a user opens a malicious repository. The notify configuration field, which specifies an external command to spawn for end-user notifications, can be set through a project-level .codex/config.toml file within an untrusted workspace. When the user runs Codex in this directory and completes an agent turn, the malicious command is executed with the user's full privileges.
Timeline
Credit
Blog Post
References
Take the first step towards securing your AI. Book a demo now and we'll reach out to you.
