CVE-2026-5817
Analyzed
Analyzed - Analysis Complete
BaseFortify
Publication date: 2026-05-22
Last updated on: 2026-06-01
Assigner: Docker Inc.
Description
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.
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.
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| docker | docker_desktop | From 4.62.0 (inc) to 4.68.0 (exc) |
Helpful Resources
Exploitability
CWE
KEV
| CWE ID | Description |
|---|---|
| CWE-829 | The product imports, requires, or includes executable functionality (such as a library) from a source that is outside of the intended control sphere. |
