CVE-2026-90553

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 arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.

Affected Software

VendorProductVersion RangeStatus
vllm-projectvLLM0 < 0.28.0affected
vllm-projectvLLM0.28.0unaffected

Weaknesses

  • CWE-94: Improper Control of Generation of Code ('Code Injection')

References