CVEvulnerability

CVE-2026-41523

7.5 HIGH Published 2026-06-22 Modified 2026-10-25 Official page ↗
Status
Modified
Published
2026-06-22
Last modified
2026-10-25
Assigner
[email protected]
CVSS 3.1 ([email protected])
7.5 HIGH — CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
CVSS 3.1 (0b0ca135-0b70-47e7-9f44-1890c2a1c46c)
7.5 HIGH — CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Weaknesses
CWE-617, CWE-94

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.

Affected configurations

• vllm vllm (< 0.22.0)

Related

Weakness · CWE (2)

  • CWE-617 Reachable Assertion weakness
  • CWE-94 Improper Control of Generation of Code weakness

References