CVEvulnerability

CVE-2026-5817

8.8 HIGH Published 2026-05-22 Modified 2026-07-23 Official page ↗
Status
Analyzed
Published
2026-05-22
Last modified
2026-07-23
Assigner
[email protected]
CVSS 4.0 ([email protected])
8.8 HIGH — 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
CVSS 3.1 ([email protected])
8.2 HIGH — CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
CVSS 3.1 ([email protected])
8.6 HIGH — CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
Weaknesses
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 configurations

• docker docker desktop (>= 4.62.0 < 4.68.0)

Related

Weakness · CWE (1)

  • CWE-829 Inclusion of Functionality from Untrusted Control Sphere weakness

References