Vulnerability · Published Sep 1, 2026 · Assigned by OAI
CVE-2026-19591
High 8.8
In plain English
A high-severity security flaw in Codex CLI from OpenAI. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 47% of all known vulnerabilities).
Official description
OpenAI Codex CLI for Windows, macOS, and Linux and Codex Desktop for Windows and macOS misclassified certain PowerShell commands as safe because their command-safety parser interpreted PowerShell's stop-parsing token (--%) differently than PowerShell itself. If a user opens an attacker-prepared repository and Codex follows its instructions, Codex can run a file-writing Git command without requesting user approval. On macOS and Linux, exploitation additionally requires separately installed PowerShell Core (pwsh) to be invoked. If filesystem protections permit the write, the command can modify Codex's configuration. If Codex later loads the modified configuration, it can launch an attacker-controlled MCP server and execute code with the user's privileges, allowing it to read, change, or delete files accessible to that account. The approval bypass does not disable filesystem sandboxing; the default filesystem sandbox on macOS and Linux can prevent writes outside permitted locations.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| OpenAI | Codex CLI | 0.72.0 – through 0.130.0 |
| OpenAI | Codex Desktop | 260202.0859 – through 26.513.31313 |
| OpenAI | Codex Desktop | 26.304.38 – through 26.513.40821 |
| OpenAI | Codex Desktop (Microsoft Store package) | 26.304.38.0 – through 26.513.4821.0 |
Weakness: CWE-150 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H