8.8
HIGH CVSS 4.0
CVE-2026-5843
Docker Model Runner container-to-host code execution via MLX-LM model_file importlib loading
Description

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.

INFO

Published Date :

May 22, 2026, 8:16 p.m.

Last Modified :

June 1, 2026, 6:07 p.m.

Remotely Exploit :

No
Affected Products

The following products are affected by CVE-2026-5843 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

ID Vendor Product Action
1 Docker desktop
2 Docker docker_desktop
1 Apple macos
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 3.1 HIGH 686469e6-3ff6-451b-ab8b-cf5b9e89401e
CVSS 3.1 HIGH MITRE-CVE
CVSS 3.1 HIGH [email protected]
CVSS 3.1 HIGH [email protected]
CVSS 4.0 HIGH 686469e6-3ff6-451b-ab8b-cf5b9e89401e
CVSS 4.0 HIGH [email protected]
Solution
Prevent arbitrary code execution by validating model files and ensuring secure loading.
  • Validate all model files before loading.
  • Implement trust checks for imported code.
  • Update MLX-LM library to a secure version.
  • Run MLX backend in a sandboxed environment.
Public PoC/Exploit Available at Github

CVE-2026-5843 has a 3 public PoC/Exploit available at Github. Go to the Public Exploits tab to see the list.

References to Advisories, Solutions, and Tools

Here, you will find a curated list of external links that provide in-depth information, practical solutions, and valuable tools related to CVE-2026-5843.

URL Resource
https://docs.docker.com/desktop/release-notes/#4710 Release Notes
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-5843 is associated with the following CWEs:

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Docker Model Runner container-to-host RCE / Escape: A critical vulnerability that allows for container-to-host code execution in the Docker Model Runner MLX / SGLANG / VLLM inference backend.

Python Shell

Updated: 3 weeks, 1 day ago
0 stars 0 fork 0 watcher
Born at : May 22, 2026, 4:30 p.m. This repo has been linked 3 different CVEs too.

Docker Container Escape POC via mlx-metal importlib

Python

Updated: 3 weeks, 1 day ago
0 stars 0 fork 0 watcher
Born at : May 20, 2026, 11:33 a.m. This repo has been linked 2 different CVEs too.

📡 PoC auto collect from GitHub. ⚠️ Be careful Malware.

security cve exploit poc vulnerability

Updated: 6 days, 3 hours ago
7810 stars 1261 fork 1261 watcher
Born at : Dec. 8, 2019, 1:03 p.m. This repo has been linked 718 different CVEs too.

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-5843 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-5843 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • Initial Analysis by [email protected]

    Jun. 01, 2026

    Action Type Old Value New Value
    Added CVSS V3.1 AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
    Added CPE Configuration AND OR *cpe:2.3:a:docker:docker_desktop:*:*:*:*:*:*:*:* versions from (including) 4.56.0 up to (excluding) 4.71.0 OR cpe:2.3:o:apple:macos:-:*:*:*:*:*:*:*
    Added Reference Type Docker Inc.: https://docs.docker.com/desktop/release-notes/#4710 Types: Release Notes
  • New CVE Received by [email protected]

    May. 22, 2026

    Action Type Old Value New Value
    Added Description 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.
    Added CVSS V4.0 AV:L/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
    Added CVSS V3.1 AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
    Added CWE CWE-829
    Added Reference https://docs.docker.com/desktop/release-notes/#4710
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.