Docker Model Runner container-to-host code execution via unsandboxed trust_remote_code in Python inference backends (Docker Docker Desktop)

CVE-2026-5817
HIGH 8.8

At a glance

Source
NVD
EPSS
EPSS 0.22 % · percentile 13 ()
State
PUBLISHED
Published
Updated
Assigner
Docker
NVD status
Analyzed

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.

Weaknesses (CWE)

  • CWE-829 — Inclusion of Functionality from Untrusted Control Sphere

References

Scores

VersionScoreVectorScored by
CVSS 4.0HIGH 8.8CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:HDocker
CVSS 3.1HIGH 8.2CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:HDocker
CVSS 4.0HIGH 8.8CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XNVD · security@docker.com (Secondary)
CVSS 3.1HIGH 8.2CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:HNVD · security@docker.com (Secondary)
CVSS 3.1HIGH 8.6CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:HNVD · nvd@nist.gov (Primary)

European references

CERT-FR advisories

Affected configurations (NVD CPE)

Affected products

ProductVersions
Docker · Docker Desktopaffected 4.62.0 < 4.68.0

Sources

SourceLicence
CVE List (CVEProject cvelistV5)CVE Program Terms of Use
EPSS (FIRST.org)FIRST — attribution requested
ENISA EUVDENISA — reproduction authorised, source acknowledged
CERT-FR (ANSSI)Licence Ouverte / Etalab 2.0
NVD (NIST) via fkie-cad/nvd-json-data-feedsPublic domain — this product uses data from the NVD API but is not endorsed or certified by the NVD