8.8
/ 10
HIGH
CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
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.
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.
AI Analysis
Arbitrary code execution vulnerability in Docker Model Runner via MLX-LM model_file importlib loading
Basic Information
ID
CVE-2026-5843
Source
Docker
Published
May 22, 2026 at 19:28
Affected Product
Vendor
Docker
Product
Docker Desktop
Version
4.56.0
Affected Versions
Docker Docker Desktop 4.56.0
CWE Classification
AI Assessment
AI Score
8.8 / 10
AI Severity
High
Vendor
Docker
Product
Docker Model Runner
Version
4.56.0