# CVE-2026-19591: Security feature bypass in Codex CLI

> Attackers can bypass approval prompts to modify configuration and execute code via malicious repositories in OpenAI Codex CLI and Desktop.

- **Severity:** High 8.8 (`CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** A user has to click or open something
- **Fix available:** No
- **Published:** 1 Sep 2026
- **Updated:** 2 Sep 2026
- **Also known as:** GHSA-2frj-4qr5-m2rf

## What is CVE-2026-19591?

CVE-2026-19591 is a high-severity vulnerability in OpenAI Codex CLI, published on 1 Sep 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.

### 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.

Weakness: CWE-150 (Improper Neutralization of Escape, Meta, or Control Sequences)

## Which versions are affected by CVE-2026-19591?


## How do I fix CVE-2026-19591?

No fix has been published for CVE-2026-19591 yet. Limit exposure of the affected software until one is available.

## Is CVE-2026-19591 being exploited?

There is no known exploitation of CVE-2026-19591 in the wild and no public exploit code.

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-19591 and fix it if it is affected.

What it is: CVE-2026-19591 is a high-severity vulnerability in OpenAI Codex CLI, published on 1 Sep 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.
Exploitation: There is no known exploitation of CVE-2026-19591 in the wild and no public exploit code.

Affected product: OpenAI Codex CLI. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-19591/ (Markdown: https://insights.sbomify.com/CVE-2026-19591/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-19591
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-19591
- OSV: https://osv.dev/vulnerability/CVE-2026-19591

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-19591/
Summaries are generated and may contain mistakes; the official description above is the record.