CVE-2026-5817
Docker Model Runner container-to-host code execution via unsandboxed trust_remote_code in Python inference backends
- Published
- May 22, 2026
- Updated
- May 27, 2026
- Assigning CNA
- Docker
- Evidence observed
- Aug 10, 2026
Primary CVSS
nvd · CVSS 4.0
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:XLow · next 30 days
- Percentile
- 13.3%
- Model date
- Sep 21, 2026
EPSS is a statistical estimate, not a certainty or a measure of impact. Combine it with CVSS, KEV status, exposure and your environment.
Summary
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.
Sources
2Docker 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.
Docker Container-to-Host Remote Code Execution POC via vllm-metal trust_remote_code=True
Responsible use
Use vulnerability information only on systems you own or are authorized to test. Kitploit links to public research metadata and does not store exploit code or malicious payloads.