CVE-2026-41523

What it is

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.

At a glance

Exploitability

Can be exploited over the network without logging in, but needs a user to act. High risk of data exposure, data tampering, service disruption.

Exploit odds

0.9% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-06-22 23:16 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-10-25 23:10 UTC Last updatedMost recent change to the record

Why it ranks here

• Exploited in the wild: no, CISA does not list it.
• Exploit odds: 0.9% in the next 30 days (EPSS).
• Severity: 7.5 HIGH (CVSS).
• Fix: a patch or advisory is linked.

Details

Published

2026-06-22 23:16 UTC

Last modified

2026-10-25 23:10 UTC

Exploit probability

0.9% · EPSS, next 30 days

Weakness

CWE-94 · Code injection

Record status

Modified

Affected

• Vllm < 0.22.0

Attack profile CVSS 3.1 · 7.5

Attack vector

Network

Complexity

High

Privileges needed

None

User interaction

Required

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Is it in your code?

Hand this to your coding agent. It searches your project for the affected products and checks versions. Nothing leaves your machine.

Read https://cve-list.com/agent/cve/CVE-2026-41523.md and follow it. Check whether this project is affected by CVE-2026-41523. Read only. Don't change anything and don't upload my code. Tell me yes, no or not sure, with the file as proof.

Copy as ticket · More options · Status badge