GHSA-XRXF-JGV3-QMRM OpenAI Codex CLI enables code execution through malicious MCP (Model Context Protocol) configuration files

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...

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 is triggered when a user runs the codex command inside a malicious or compromised repository. Codex automatically loads...

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 is triggered when a user runs the codex command inside a malicious or compromised repository. Codex automatically loads...

OpenAI Codex CLI 安全漏洞

OpenAI Codex CLI is a lightweight coding agent software developed by OpenAI and run in the terminal. OpenAI Codex CLI versions prior to v0.23.0 have security vulnerabilities; these vulnerabilities stem from automatically loading malicious MCP configuration files, which may allow arbitrary code to...

CVE-2025-61260

The CVE-2025-61260 issue affects the OpenAI Codex CLI, specifically versions prior to 0.23.0. The root cause is improper handling of repository-local configuration files (notably .env and .codex/config.toml) that are loaded automatically when the codex command is executed in a malicious or compro...

Exploit for CVE-2025-59532

CVE-2025-59532 Docker Environment A Docker-based research env...

Exploit for CVE-2025-61260

OpenAI Codex CLI Vuln...

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

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 session. This log...

CVE-2025-55345

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...

CVE-2025-55345

CVE-2025-55345 concerns OpenAI Codex CLI when used in a restricted workspace-write sandbox. The issue arises because symlinks are followed outside the allowed current working directory in a malicious context (repo/directory), enabling arbitrary file overwrite and potentially remote code execution...

OpenAI Codex CLI 安全漏洞

OpenAI Codex CLI is an OpenAI open source lightweight coding agent software that runs in the terminal. A security vulnerability exists in OpenAI Codex CLI that stems from the fact that use of Codex CLI in a malicious context could lead to arbitrary file overwriting and potential remote code...

PT-2025-32971 · Codex Cli · Codex Cli

Name of the Vulnerable Software and Affected Versions: Codex CLI affected versions not specified Description: Using Codex CLI in workspace-write mode within a malicious context repository, directory, etc. may lead to arbitrary file overwrite and potentially remote code execution. This occurs...

CVE-2025-54558

OpenAI Codex CLI before 0.9.0 auto-approves ripgrep aka rg execution even with the --pre or --hostname-bin or --search-zip or -z flag...

OpenAI Codex CLI 安全漏洞

OpenAI Codex CLI is an OpenAI open source lightweight coding agent software that runs in the terminal. A security vulnerability exists in OpenAI Codex CLI versions prior to 0.9.0 that stems from automatic approval of ripgrep execution, which could lead to a security risk...

CVE-2025-54558

OpenAI Codex CLI before 0.9.0 auto-approves ripgrep aka rg execution even with the --pre or --hostname-bin or --search-zip or -z flag...