SEPTEMBER 13, 2026
Live Feed
Back to database
Case File

CVE-2026-90553

HIGH · CVSS 7.8 EPSS 0.21% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-09-12 · Last synced 2026-09-13

CyberRota Analysis

AI-Generated

vLLM versions prior to 0.28.0 are vulnerable to a remote code execution flaw in the LlavaOnevision2 processor loader, which improperly handles the trust_remote_code parameter, allowing attackers to execute arbitrary code. This vulnerability poses a significant risk as it enables the execution of malicious models with elevated privileges, potentially compromising the integrity of the vLLM process. Organizations using vLLM should prioritize patching to version 0.28.0 or later to mitigate this high-severity threat.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Detected Signals
remote code execution code execution
GitHub PoC Links

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-90553
Severity
HIGH
CVSS
7.8
EPSS
0.21%

Original NVD Description

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.