CVE-2026-5843

EIP tracks 1 public exploit for CVE-2026-5843. PoCs published by davidrxchester.

AI-analyzed exploit summary This repository contains a functional exploit for CVE-2026-5843, which leverages a malicious OCI registry to serve a model that exploits the `model_file` importlib execution path in mlx-lm, leading to remote code execution on the host system when Docker Model Runner loads the model for inference.

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.