CVE-2026-5817

Affects: vLLM

CVSS: HIGH · 8.2 v3.1
CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
Published: 2026-05-22
Weakness: CWE-829
Source: nvd.nist.gov/vuln/detail/CVE-2026-5817

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.

References

https://docs.docker.com/desktop/release-notes/#4680

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-5817 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course → · Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming