OpenAI @openai/codex vulnerabilities

Latest OpenAI @openai/codex CVEs

Newest publication first

1. CVE-2025-61260 OpenAI Codex CLI enables code execution through malicious MCP (Model Context Protocol) configuration files

   Published 2026-04-14

   Critical·CVSS 9.8 EPSS 6.9%

   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 aut...

2. CVE-2025-59532 Codex has sandbox bypass due to bug in path configuration logic

   Published 2025-09-22

   High·CVSS 8.6 EPSS 0.89%

   Codex CLI is a coding agent from OpenAI that runs locally. In versions 0.2.0 to 0.38.0, due to a bug in the sandbox configuration logic, Codex CLI could treat a model-generated cwd as the sandbox’s writable root, including paths outside of the folder where the user started their...

3. CVE-2025-55345 Unsafe symlink following in restricted workspace-write sandbox leads to RCE

   Published 2025-08-13

   High·CVSS 8.8 EPSS 0.90%

   Using Codex CLI in workspace-write mode inside a malicious context (repo, directory, etc) could lead to arbitrary file overwrite and potentially remote code execution due to symlinks being followed outside the allowed current working directory.

Sources: CVE.org, NVD, CISA KEV, FIRST EPSS, OSV and public exploit-reference metadata. Product matching comes from the published CVE records. A proof-of-concept means public code exists; it is not evidence of exploitation.