---
id: CVE-2026-5843
title: >-
  The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM
  library, which unconditionally imports and executes arbitrary Python files
  from model directories via the model_file configuration field in config.json
summary: >-
  The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM
  library, which unconditionally imports and executes arbitrary Python files
  from model directories via the model_file configuration field in config.json.
  When a mod…
severity: high
cvss: 8.2
cvssVector: 'CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H'
cwe:
  - CWE-829
vendor: docker
product: docker_desktop
affected:
  - 'docker_desktop >= 4.56.0, < 4.71.0'
patched:
  - docker_desktop 4.71.0
published: '2026-05-22'
updated: '2026-07-23'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-5843'
references:
  - url: 'https://docs.docker.com/desktop/release-notes/#4710'
    label: security@docker.com
tags:
  - nvd
  - exploit-available
epss: 0.00184
epssPercentile: 0.07074
ingestedAt: '2026-07-23T11:17:34.134Z'
exploits:
  github: 1
  githubRepos:
    - 'https://github.com/davidrxchester/CVE-2026-5843'
  checkedAt: '2026-09-25T08:21:04.813Z'
exploitAvailable: true
---

## Overview

The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM library, which unconditionally imports and executes arbitrary Python files from model directories via the model_file configuration field in config.json. When a model's config.json specifies a model_file pointing to a Python file, MLX-LM uses importlib to load and execute it with no trust_remote_code gate or equivalent safety check. The MLX backend runs without sandboxing, resulting in arbitrary code execution on the Docker host as the Docker Desktop user.

Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model from an attacker-controlled OCI registry and request inference.

## Affected

- `docker_desktop >= 4.56.0, < 4.71.0`

## Remediation

Upgrade past the affected range:

- `docker_desktop 4.71.0`