CVE-2026-41523: vllm-project vllm Code Injection

Vulnerability summary

CVE-2026-41523 is a high (CVSS 7.5) Code Injection vulnerability in vllm-project vllm. EPSS estimates a 0.91% chance of exploitation in the next 30 days, higher than 59.6% of scored vulnerabilities. 1 public exploit is recorded.

Timeline

1. 22-06-2026
   PublishedVulnerability first disclosed.
2. 04-09-2026
   Last modifiedVulnerability information updated.

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.

• CWE-94Improper Control of Generation of Code ('Code Injection')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-617Reachable AssertionThe 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.