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 sandboxing.
Published May 22, 2026 · corrected/updated Jul 23, 2026 · docker docker desktop · evidence confidence medium
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.
Grounded briefings
Catalog interpretations for three audiences. Each brief cites ingested metadata and the original advisories below. They are not independent research and they do not invent exploit steps.
Executive
CVE-2026-5817 is a high public vulnerability record for docker docker desktop. It is not currently listed in the CISA Known Exploited catalog. Check the linked vendor or CERT advisories for patch status. This summary is a catalog interpretation of the ingested metadata and cites the original advisories below.
System administrator
Identify whether docker docker desktop is in your estate, then compare installed versions with the affected ranges. Affected packages or ranges on record: docker/docker desktop. Check the linked vendor or CERT advisories for patch status. Prefer the vendor or distribution advisory linked in Sources before changing production systems. This is a catalog interpretation, not a runbook.
Security analyst
Signals on file: CVSS 8.8. It is not currently listed in the CISA Known Exploited catalog. Weakness classes: CWE-829. Sources contributing to this record: cve_org, nvd. Public exploit references, when present, are outbound links only and are not proof of active exploitation. This is a catalog interpretation of stored metadata.
Exploitation and remediation
Exploitation evidence
Not listed as known exploited in CISA KEV. Not in the CISA KEV catalog.
Patch and remediation
No required-action text is stored yet. Use the vendor or CERT links in Sources for patch availability.
Safe detection guidance
Compare installed versions with the affected ranges below and verify the advisory from the original publisher. This site stores metadata and outbound links only; it does not ship exploit code or proof-of-concept payloads.
Technology hubs
Code
The project this record applies to. Exploit listings stay in References.
No public source repository is identified for this product.
Timeline
Detection, updates, and resolution for this record.
May 22, 2026 · NIST NVD
Detected
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
Jul 23, 2026 · NIST NVD
Updated
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
Affected
- cpe docker/docker desktopversion unspecified
Sources
- CVE.orgVulnerability recordCVE-2026-5817
Official CVE identifier
cve.org - NIST NVDVulnerability recordCVE-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 sandboxing. This causes transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included
nvd.nist.gov