CVE-2026-5817 (CVSS 8.2)

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.

Is your site exposed to CVE-2026-5817?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

8.2

HIGH

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

EPSS — Exploit Prediction

0.0021

Probability of exploitation

0.11%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-829 CWE-829

References

Other References

https://docs.docker.com/desktop/release-notes/#4680

Frequently Asked Questions

What is 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. 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. It has a CVSS v3.1 base score of 8.2 (HIGH).

How severe is CVE-2026-5817? +

CVE-2026-5817 has a CVSS v3.1 score of 8.2 out of 10, rated HIGH. This is a high-severity vulnerability that should be prioritized for patching. The EPSS score is 0.0021, placing it in the 0th percentile for exploitation probability.

How do I check if I'm vulnerable to CVE-2026-5817? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2025-34074

An authenticated remote code execution vulnerability exists in Lucee’s administrative interface due to insecure design in the scheduled task functionality. …

CVE-2026-59865

Kiota is an OpenAPI based HTTP Client code generator. Prior to 1.32.5, `kiota info` read x-ms-kiota-info.languagesInformation.<language>.dependencyInstallCommand plus dependency name and …

CVE-2025-34060

A PHP objection injection vulnerability exists in the Monero Project’s Laravel-based forum software due to unsafe handling of untrusted input …

CVE-2026-59864

Kiota is an OpenAPI based HTTP Client code generator. Prior to 1.32.5, `kiota plugin add` and `kiota plugin generate` (with …

CVE-2025-36852

A critical security vulnerability exists in remote cache extensions for common build systems utilizing bucket-based remote cache (such as those …

CVE-2026-0303

A code execution vulnerability in Palo Alto Networks Checkov by Prisma® Cloud can allow arbitrary code execution when Checkov scans …

CVE-2026-5817