CVE-2026-5817
Severity CVSS v4.0:
HIGH
Type:
Unavailable / Other
Publication date:
22/05/2026
Last modified:
01/06/2026
Description
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.<br />
<br />
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.
Impact
Base Score 4.0
8.80
Severity 4.0
HIGH
Base Score 3.x
8.20
Severity 3.x
HIGH
Vulnerable products and versions
| CPE | From | Up to |
|---|---|---|
| cpe:2.3:a:docker:docker_desktop:*:*:*:*:*:*:*:* | 4.62.0 (including) | 4.68.0 (excluding) |
| cpe:2.3:o:apple:macos:-:*:*:*:*:*:*:* |
To consult the complete list of CPE names with products and versions, see this page



