Vulnerability in Apple macOS
CVE-2026-5817
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.
EPSS: 0.002 (12.9th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 8.2 (High). Vector: CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H.
Affected products
- Apple Macos
- Docker Desktop — versions 4.62.0
- Docker Docker_desktop
Weakness classification (CWE)
Public proof-of-concept exploits
References
- security@docker.com (release-notes, Release Notes)
Frequently asked questions
- What is CVE-2026-5817?
- CVE-2026-5817 is a high-severity vulnerability in Apple macOS, classified under Inclusion of Functionality from Untrusted Control Sphere. CVSS score: 8.2/10. Published 2026-05-22.
- How severe is CVE-2026-5817?
- High severity. CVSS v3 base score is 8.2 out of 10.
- Is CVE-2026-5817 known to be exploited?
- 2 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.