RCE in Vllm

CVE-2026-41523

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.

Vulnerability class: RCE (Remote Code Execution)

Published · last modified .

CVSS v3 metric

CVSS v3 base score 7.5 (High). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H.

EPSS exploit prediction

EPSS: 0.009 (58.5th percentile), scored .

Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 59th percentile — 58.5% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.

EPSS trend (30 days)EPSS over the last 30 days for CVE-2026-41523: held from 0.009 to 0.009.

EPSS over last 30 days · oldest: 0.009 · newest: 0.009 · change: 0.000

Affected products

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2026-41523?
CVE-2026-41523 is a high-severity vulnerability in Vllm, classified under Code Injection. CVSS score: 7.5/10. Published 2026-06-22.
How severe is CVE-2026-41523?
High severity. CVSS v3 base score is 7.5 out of 10.