HIGH · 8.2

CVE-2026-5817

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...

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

8.2

HIGH

CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
Attack Vector
LOCAL
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
REQUIRED
Scope
CHANGED
Confidentiality
HIGH
Integrity
HIGH
Availability
HIGH

Affected Products

VendorProductVersions
DockerDocker Desktop>= 4.62.0, < 4.68.0
AppleMacos-

Related Weaknesses (CWE)

References

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.