Vulnerability record · CVE-2026-41523 · published 22 June 2026
CVE-2026-41523: Vllm code injection vulnerability
Vllm · Vllm
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.
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.
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Affected products
1 vulnerable configurations from NVD's CPE data, grouped by vendor and product.
References
Track CVE-2026-41523 inside VULONE
Watch it alongside the ransomware crews, C2 infrastructure and forum chatter that reference it, query it through the API and pull it into your SIEM over TAXII.
Related vulnerabilities
Same products first, then exploited flaws of the same weakness class.
Source: NIST National Vulnerability Database (record CVE-2026-41523), CISA KEV, FIRST EPSS (scores of 2026-09-27). This page is refreshed as NVD updates the record.
