What’s Vulnerable › Vulnerabilities
CVE-2026-5817: Docker Model Runner container-to-host code execution via unsandboxed trust_remote_code in Python inference backends
- Severity: high (CVSS 8.6 v3.1)
- Exploited in the wild: not listed in CISA KEV
- EPSS: 0.2% probability of exploitation in the next 30 days
- Public exploit or detection template: none known
- Published: 2026-05-22 · updated 2026-07-23
- Weakness: CWE-829
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.
Affected products
- Docker Inc. Docker Desktop: from 4.62.0 before 4.68.0 — fixed in 4.68.0
How to fix
Upgrade to a fixed version: Docker Inc. Docker Desktop 4.68.0. Check the vendor advisory for mitigations.
References
Get alerted when CVE-2026-5817 or the next vulnerability affects your stack