PT-2026-50140 · Vllm · Vllm

·

CVE-2026-41523

·

Published

2026-06-16

·

Updated

2026-07-07

CVSS v3.1

7.5

High

VectorAV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.22.0
Description An assert-based security check in the activation function loading process allows an unauthenticated attacker to achieve arbitrary code execution on the server. This occurs when vLLM is run in Python optimized mode (python -O or PYTHONOPTIMIZE=1), as Python strips assert statements at compile time in this mode. An attacker can exploit this by publishing a malicious HuggingFace model with a crafted config.json. The attacker-controlled function name is passed to the resolve obj by qualname() function, which acts as an unrestricted import gadget, executing arbitrary code during model initialization with the privileges of the vLLM process.
The vulnerable parameters within the model's config.json are config.sentence transformers["activation fn"] and config.sbert ce default activation function.
Recommendations Update to version 0.22.0. As a temporary workaround, avoid running vLLM in Python optimized mode (python -O or PYTHONOPTIMIZE=1) when loading models from untrusted sources.

Exploit

Fix

Assertion Failure

Code Injection

Found an issue in the description? Have something to add? Feel free to write us 👾

Weakness Enumeration

Related Identifiers

CVE-2026-41523
GHSA-Q8GQ-377P-JQ3R
PYSEC-2026-2300

Affected Products

Vllm