8.8

CVE-2026-5817

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

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.
Daten sind bereitgestellt durch National Vulnerability Database (NVD)
Docker ≫ Docker Desktop Version >= 4.62.0 < 4.68.0
   Apple ≫ macOS Version-
VulnDex Vulnerability Enrichment
Diese Information steht angemeldeten Benutzern zur Verfügung. Login Login
Zu dieser CVE wurde keine Warnung gefunden.
EPSS Metriken
Typ Quelle Score Percentile
EPSS FIRST.org 0.22% 0.129
CVSS Metriken
Quelle Base Score Exploit Score Impact Score Vector String
nvd@nist.gov 8.6 1.8 6
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
security@docker.com 8.8 0 0
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/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:X
security@docker.com 8.2 1.5 6
CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
CWE-829 Inclusion of Functionality from Untrusted Control Sphere

The product imports, requires, or includes executable functionality (such as a library) from a source that is outside of the intended control sphere.

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