---
id: CVE-2026-90553
title: >-
  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
summary: >-
  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 arbi…
severity: high
cvss: 7.8
cvssVector: 'CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H'
cwe:
  - CWE-94
vendor: vllm
product: vllm
affected:
  - vllm < 0.28.0
patched:
  - vllm 0.28.0
published: '2026-09-12'
updated: '2026-09-16'
sourceUpdated: '2026-09-16T17:31:40.200'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-90553'
references:
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-3c86-2m5g-59q7
    label: disclosure@vulncheck.com
  - url: >-
      https://www.vulncheck.com/advisories/vllm-before-0.28.0-remote-code-execution-via-llavaonevision2-processor
    label: disclosure@vulncheck.com
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-90553.json
  - url: 'https://access.redhat.com/security/cve/CVE-2026-90553'
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2532579'
  - url: 'https://www.cve.org/CVERecord?id=CVE-2026-90553'
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-90553'
tags:
  - nvd
  - cve.org
  - csaf
  - vex
  - red-hat
  - osv
  - pip
epss: 0.00207
epssPercentile: 0.11118
ssvc:
  exploitation: none
  automatable: 'no'
  technicalImpact: total
  timestamp: '2026-09-14T18:25:25.303206Z'
ingestedAt: '2026-09-14T15:23:07.479Z'
aliases:
  - PYSEC-2026-3985
  - GHSA-3c86-2m5g-59q7
ecosystem: pip
---

## Overview

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

- `vllm < 0.28.0`

## Remediation

Upgrade past the affected range:

- `vllm 0.28.0`

## Vendor advisories

- **Red Hat VEX** · Important · affected: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · no fix planned: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · updated 2026-09-16 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-90553.json)

## Package advisory (CVE-2026-90553)

Affected packages:

- `vllm < 0.28.0`

Patched in:

- `vllm 0.28.0`

Source: https://osv.dev/vulnerability/PYSEC-2026-3985