CVE 7.5 HIGH

vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution_CVE-2026-41523

7.5 / 10
HIGH
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H

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.

Basic Information

ID CVE-2026-41523
Source GitHub_M
Published Jun 22, 2026 at 22:18

Affected Product

Vendor vllm-project
Product vllm
Version < 0.22.0
Affected Versions vllm-project vllm < 0.22.0

CWE Classification

References

💭 Join the Security Discussion

🔒 Your email address will not be published. Required fields are marked *

⚠️ Please be respectful and constructive in your comments. Security discussions should remain professional.