CVE-2026-5817The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sandboxing.
Updated under an hour ago ()
Does this affect you?
It affects docker_desktop. Add what you run to find out whether that includes you.
No exploitation reported and no EPSS estimate yet.
Do this next
Free account, 1 product
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
- 8.6 HIGH (v3.1, NVD)CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
- Weakness (CWE)
- CWE-829
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- Not loaded for this CVE
- Assigned by
- Not given
- NVD analysis
- Analyzed
- Record last updated
- Jul 23, 2026
- First seen by InfoSec Signals
- Oct 9, 2026
Affected products
docker docker_desktop docker:docker_desktop | from 4.62.0 before 4.68.0 | NVD |
References
- https://docs.docker.com/desktop/release-notes/#4680release-notes
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.