CVE Database
/

CVE-2026-5817

Back to search

CVE-2026-5817

Published: May 22, 2026

Modified: May 27, 2026

PUBLISHED

CVSS v3.1

8.2

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.

VendorProductVersions

Docker

Docker Desktop

affected
4.62.0 - < 4.68.0

Weaknesses (CWE)

CVSS v3.1 Details

CVSS v3.1 Vector

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

Attack Vector

Local

Attack Complexity

Low

Privileges Required

Low

User Interaction

Required

Scope

Changed

Confidentiality

High

Integrity

High

Availability

High

Security Training

Train your team to recognize and prevent security threats with our comprehensive security awareness program.

Start Training

Vulnerability Scanning

Discover vulnerabilities in your applications and infrastructure before attackers do.

Scan Now