CVE-2026-90553

published 12 Sep 2026 · updated 14 Sep 2026

vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor

7.8HighCVSS 7.8EPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in 0.28.0.

vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
vllm-project<0.28.00.28.0

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-90553 severity on Zeptric[![CVE-2026-90553](https://zeptric.io/badge/cve/CVE-2026-90553.svg)](https://zeptric.io/cve/CVE-2026-90553)