Vulnerability 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 Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Docker | Docker Desktop | >= 4.62.0, < 4.68.0 |
| Apple | Macos | - |
Related Weaknesses (CWE)
References
- https://docs.docker.com/desktop/release-notes/#4680Release Notes
FAQ
What is CVE-2026-5817?
CVE-2026-5817 is a vulnerability with a CVSS score of 8.2 (HIGH). 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.AutoTo...
How severe is CVE-2026-5817?
CVE-2026-5817 has been rated HIGH with a CVSS base score of 8.2/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-5817?
Check the references section above for vendor advisories and patch information. Affected products include: Docker Docker Desktop, Apple Macos.