Docker Model Runner container-to-host code execution via unsandboxed trust_remote_code in Python inference backends
No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in Desktop 4.68.0.
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 transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included in any model pulled from an OCI registry, resulting in arbitrary code execution on the Docker host as the Docker Desktop user when inference is triggered. Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model and request inference.
Affected
Vendors, products and packages with version ranges
| Vendor | Product | Versions | Fixed |
|---|---|---|---|
| Docker | Desktop | >=4.62.0 <4.68.0 | 4.68.0 |
Timeline
Every event on this vulnerability
Related
Other vulnerabilities in Docker, strongest first
Embed
A live severity badge for an advisory, README or ticket