CVE-2026-41523
Received Received - Intake
Arbitrary Code Execution in vLLM via Malicious Model

Publication date: 2026-06-22

Last updated on: 2026-06-22

Assigner: GitHub, Inc.

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 Scores
EPSS Scores
Probability:
Percentile:
Meta Information
Published
2026-06-22
Last Modified
2026-06-22
Generated
2026-06-23
AI Q&A
2026-06-23
EPSS Evaluated
N/A
NVD
CVE-2026-41523
Affected Vendors & Products
Currently, no data is known.
Helpful Resources
Exploitability
CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-94 The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.
CWE-617 The product contains an assert() or similar statement that can be triggered by an attacker, which leads to an application exit or other behavior that is more severe than necessary.
Attack-Flow Graph
AI Quick Actions
Instant insights powered by AI
Executive Summary

The vulnerability exists in vLLM, an inference and serving engine for large language models. Prior to version 0.22.0, an assert-based security check in the activation function loading process can be bypassed when vLLM is run in Python optimized mode (using python -O or PYTHONOPTIMIZE=1). This allows any unauthenticated attacker to execute arbitrary code on the server by publishing a malicious HuggingFace model.

Impact Analysis

This vulnerability can lead to arbitrary code execution on the server running vLLM, which means an attacker could potentially take full control of the server, compromise data, disrupt services, or use the server as a foothold for further attacks.

Mitigation Strategies

To mitigate this vulnerability, upgrade vLLM to version 0.22.0 or later, where the issue has been fixed.

Avoid running vLLM in Python optimized mode (using python -O or setting PYTHONOPTIMIZE=1) until the upgrade is applied.

Chat Assistant
Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-41523. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70
EPSS Chart