CVE WatchJul 15, 2026

CVE-2026-41523

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 activati

CVSS

7.5

High

EPSS

0.5%

p39

KEV

—

Exploit Today

0-100

Published: Jun 22, 2026 · Last modified: Jul 15, 2026 · CWE-94 · CWE-617

EPSS · 30d

0.5%EPSS · 30 days0.5%

2026-06-302026-07-17

Technical 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.

Official references

Related CVEs

CVECVSSEPSSKEVRExploitTitleMod.

CVE-2025-32489.8 CRI

100.0%

KEV—80Langflow Missing Authentication Vulnerability4d CVE-2026-341978.8 HIG

99.9%

KEV—80Apache ActiveMQ Improper Input Validation Vulnerability3d CVE-2026-154107.2 HIG

71.1%

KEV—71SonicWall SMA1000 Appliances Code Injection Vulnerability2d CVE-2025-670389.8 CRI

55.3%

KEV—67Lantronix EDS5000 Code Injection Vulnerability12d CVE-2021-416539.8 CRI

99.5%

——30The PING function on the TP-Link TL-WR840N EU v5 router with firmware through TL-WR840N(EU)_V5_171211 is vulnerable to remote code execution via a crafted payload in an IP address input field.9d CVE-2023-362558.8 HIG

99.0%

——30An issue in Eramba Limited Eramba Enterprise and Community edition v.3.19.1 allows a remote attacker to execute arbitrary code via the path parameter in the URL.9d