PoC Index

CVE-2026-5817

HIGH 8.8EPSS 0.2%

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 v4.0
8.8 HIGHCVSS: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 v3.1
8.6 HIGHCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
CVSS v3.1
8.2 HIGHCVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
EPSS
0.22% chance of exploitation in the next 30 days, 13th percentile
Published
2026-05-22
Updated
2026-05-27

Proof-of-concept exploits (2)

References

Related