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.
[POC] CVE-2026-5817 — CVE-2026-5817-PoC
Docker Model Runner container-to-host RCE / Escape: A critical vulnerability that allows for container-to-host code execution in the Docker Model Runner MLX / SGLANG / VLLM inference backend.
PoC: CVE-2026-5817
Docker Container-to-Host Remote Code Execution POC via vllm-metal trust_remote_code=True
CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
Get alerted for CVEs like this
Register your stack and get notified within minutes when a matching CVE drops.
Start monitoring free