Strix
26.1K

CVE-2026-5817

HIGHCVSS 8.8/10EPSS 0.22%

Last modified

CVE-2026-5817 is a high-severity vulnerability rated 8.8/10 on the CVSS scale. 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.. EPSS estimates a 0.22% chance of exploitation in the next 30 days.

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.

Metrics

CVSS 3.1
8.6/10

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

CVSS 4.0
8.8/10

CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

EPSS Probability
0.22%

13.0th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

VendorProductVersions
DockerDocker Desktop>= 4.62.0, < 4.68.0

References

Timeline

Published
Last Modified
Status
Analyzed

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.
How severe is CVE-2026-5817?
CVE-2026-5817 has a CVSS score of 8.8/10 (HIGH severity). The EPSS model estimates a 0.22% probability of exploitation in the next 30 days.
How do I fix CVE-2026-5817?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

Are you affected by CVE-2026-5817?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST