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 …
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.
Metrics
Weakness classes (CWE)
CWE-829Base
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.
cwe.mitre.org →
Reanalysis & status changes
Chronological NVD audit events for this CVE — reanalyses, CVSS updates, CPE diffs.
- CVE Translated2026-07-23 11:10 UTC· nvd@nist.gov
- Translation: Title: Docker Desktop de Docker, Description: El backend de inferencia vllm-metal en Docker Model Runner en macOS establece incondicionalmente trust_remote_code=True al cargar tokenizadores de modelos, y se ejecuta sin sandboxing. Esto provoca que transformers.AutoTokenizer.from_pretrained() importe y ejecute archivos Python arbitrarios incluidos en cualquier modelo extraído de un registro OCI, lo que resulta en ejecución de código arbitrario en el host de Docker como el usuario de Docker Desktop cuando se activa la inferencia. Cualquier contenedor en la red de Docker puede activar esto llamando a la API model-runner.docker.internal para extraer un modelo malicioso y solicitar inferencia.
Affected products
Products and version ranges extracted from the vendor/CERT advisory. A range like „<4.14.6“ implies the update recommendation „upgrade to 4.14.6 or later“.
docker
docker_desktop4.62.0 – 4.68.0