← לוח פגיעויות

CVE-2026-5817

גבוהה 8.6

תיאור (מקור, אנגלית)

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.

מדדים

CVSS 3.1
8.6 (HIGH) מקור הציון: NVD CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
CVSS 4.0
8.8 (HIGH) מקור הציון: CNA 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
EPSS — סבירות ניצול
0% (אחוזון 000) נכון ל-5/8/2026
CWE
CWE-829

מוצרים מושפעים

docker: docker desktop; apple: macos

קישורים