CVE-2026-41523

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.

Severity
HIGH
CVSS v3
7.5
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H · source cna
Exploit chance (EPSS)
0.913%
chance of exploitation in the next 30 days
higher than 60.7% of scored CVEs · 2026-11-17
CISA KEV
Not listed
Public exploit code
Yes
Exploit references (NVD and CNA): 1
Metasploit modules: 0
Nuclei templates: 0

Weakness

CISA SSVC decision points

Exploitationnone
Automatableno
Technical impacttotal
Scored2026-06-23

Timeline

  1. 2026-06-16GitHub advisory published (GHSA-q8gq-377p-jq3r)6 days before publication
  2. 2026-06-22Published by the CNA22:18 UTC
  3. 2026-06-23CISA SSVC decision recorded1 day after publication

The timeline shows what already happened. To be told when this CVE changes next, watch it from the API.

Exploit and advisory records

GitHub advisory GHSA-q8gq-377p-jq3r, affected packages:

PackageVulnerable versionsFixed in
PyPI vllmbefore 0.22.00.22.0

Affected products

Products listed as vulnerable. Upgrade to the version under "Fixed in", or a later one.

ProductVulnerable versionsFixed in
vllm vllmbefore 0.22.0fixed in 0.22.00.22.0

Products and versions as NVD and the vendor that published the CVE list them.

References

Get more CVE data from the API.

Free without a key or signup. Pro adds monitoring and higher limits: pricing.

Sources