Docker Model Runner vulnerabilities

Docker Model Runner prior to version 1.1.25 contains an SSRF vulnerability in the OCI registry token exchange flow where Model Runner follows the realm URL from the WWW-Authenticate header without validating scheme, hostname, or IP range. A malicious OCI registry can set the realm to an internal URL, causing requests to internal services and reflecting responses. The issue is patched in version 1.1.25.

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. No sandboxing allows remote code execution on the Docker host as the Docker Desktop user.

The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers and runs without sandboxing. This causes arbitrary Python file execution from the model, enabling remote code execution on the Docker host as the Docker Desktop user.