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.
This vulnerability carries a HIGH severity rating with a CVSS v3.1 score of 8.2, requiring local system access to exploit with relatively low complexity though user interaction is required requiring only low-level privileges . The vulnerability impacts confidentiality (data exposure), integrity (unauthorized modifications), and availability (service disruption) for affected systems. Impacting 2 products from docker, from apple organizations running these solutions should prioritize assessment and patching.
Reported in 2026, this vulnerability emerged during an era marked by increased sophistication in supply chain attacks, cloud infrastructure vulnerabilities, and software-as-a-service (SaaS) security challenges. Security practices during this period emphasized zero-trust architectures, container security, and API protection.
2026-05-22T20:16:35.120
2026-06-01T18:08:14.170
Analyzed
CVSSv3.1: 8.2 (HIGH)
| Type | Vendor | Product | Version/Range | Vulnerable? |
|---|---|---|---|---|
| Application | docker | docker_desktop | < 4.68.0 | Yes |
| Operating System | apple | macos | - | No |
SecUtils normalizes and enriches National Vulnerability Database (NVD) records by standardizing vendor and product identifiers, aggregating vulnerability metadata from both NVD and MITRE sources, and providing structured context for security teams. For docker's affected products, we extract Common Platform Enumeration (CPE) data, Common Weakness Enumeration (CWE) classifications, CVSS severity metrics, and reference data to enable rapid vulnerability prioritization and asset correlation. This record contains no exploit code, proof-of-concept instructions, or attack methodologies—only defensive intelligence necessary for patch management, risk assessment, and security operations.