A AegiFlow
HIGHCVSS 7.5EPSS 0.9%

CVE-2026-41523

CVE-2026-41523 updated by NVD

Published
2026-06-16
Modified
2026-09-06
EPSS percentile
58%
Sources
github-advisory, nvd

Summary

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 packages

EcosystemPackageAffected versionsFixed versions
PyPIvllm0.22.0

Remediation: Upgrade to 0.22.0 or later.

References

Includes data from the GitHub Advisory Database, licensed under CC-BY 4.0.

Includes data from the National Vulnerability Database (NIST). NVD data is in the public domain; this page is not endorsed by NIST.

CVE® is a registered trademark of The MITRE Corporation. CVE content reproduced under the CVE Terms of Use; copyright designation © MITRE.

EPSS scores provided by the FIRST.org Exploit Prediction Scoring System.