You are viewing this page in an unauthorized frame window.
This is a potential security issue, you are being redirected to
https://nvd.nist.gov
An official website of the United States government
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock () or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.
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
NVD enrichment efforts reference publicly available information to associate
vector strings. CVSS information contributed by other sources is also
displayed.
By selecting these links, you will be leaving NIST webspace.
We have provided these links to other web sites because they
may have information that would be of interest to you. No
inferences should be drawn on account of other sites being
referenced, or not, from this page. There may be other web
sites that are more appropriate for your purpose. NIST does
not necessarily endorse the views expressed, or concur with
the facts presented on these sites. Further, NIST does not
endorse any commercial products that may be mentioned on
these sites. Please address comments about this page to [email protected].
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.
AND
OR
*cpe:2.3:a:docker:docker_desktop:*:*:*:*:*:*:*:* versions from (including) 4.62.0 up to (excluding) 4.68.0
OR
cpe:2.3:o:apple:macos:-:*:*:*:*:*:*:*
New CVE Received from Docker Inc.5/22/2026 4:16:35 PM
Action
Type
Old Value
New Value
Added
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.