HIGH 8.5 NVD
CVE-2026-90553
vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when load
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.
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-3c86-2m5g-59q7
- https://www.vulncheck.com/advisories/vllm-before-0.28.0-remote-code-execution-via-llavaone
This high severity vulnerability with a CVSS score of 8.5 was published on 2026-09-12 via NVD.
vulnfeed aggregates 12843 vulnerabilities from NVD, CISA KEV,
Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.