Detections
Analytics

CVE-2026-5817

high

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.

References

https://docs.docker.com/desktop/release-notes/#4680

Details

Source: Mitre, NVD

Published: 2026-05-22

Updated: 2026-06-01

Risk Information

CVSS v2

Base Score: 7.2

Vector: CVSS2#AV:L/AC:L/Au:N/C:C/I:C/A:C

Severity: High

CVSS v3

Base Score: 8.6

Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

Severity: High

CVSS v4

Base Score: 8.8

Vector: CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

Severity: High

EPSS

EPSS: 0.00014