CVE-2026-5817
Docker Model Runner container-to-host code execution via unsandboxed trust_remote_code in Python inference backends
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.
CVSS Vector Breakdown
AV:LAttack VectorAC:LAttack ComplexityPR:LPrivileges RequiredUI:RUser InteractionS:CScopeC:HConfidentialityI:HIntegrityA:HAvailabilityWeaknesses
Affected Products
Attack Graph
Click technique nodes to view MITRE ATT&CK details. Scroll to zoom, drag to pan.
Exploitability
MITRE ATT&CK
1 techniqueReferences
Timeline
Unlock Complete Vulnerability Intelligence
Get the full picture for CVE-2026-5817 and every CVE in our database. Create a free account — no credit card required.
Create Free Account