Description
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.
Affected products
vllm: vllm
References10
- github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb2138… Patch
- github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p… ExploitThird Party Advisory
- huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c Third Party Advisory
- access.redhat.com/errata/RHSA-2026:36005
- access.redhat.com/errata/RHSA-2026:36006
- access.redhat.com/errata/RHSA-2026:57380
- access.redhat.com/errata/RHSA-2026:57387
- access.redhat.com/errata/RHSA-2026:57389
- access.redhat.com/errata/RHSA-2026:57390
- access.redhat.com/errata/RHSA-2026:59138
Metrics
- CVSS 3.1
-
7.5
HIGH
Score source: CNA
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H - EPSS — exploit probability
- 1% percentile: 61 · as of 16 November 2026
- CWE
- CWE-94CWE-617
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.