RCE in Vllm
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 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.
Vulnerability class: RCE (Remote Code Execution)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.8 (High). Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS: 0.003 (23.5th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 23rd percentile — 23.5% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.003 · newest: 0.003 · change: 0.000
Affected products
Weakness classification (CWE)
References
- github.com/vllm-project/vllm/security/advisories/GHSA-3c86-2m5g-59q7 (vendor-advisory, Vendor Advisory)
- www.vulncheck.com/advisories/vllm-before-0.28.0-remote-code-execution-via-llava… (Third Party Advisory, third-party-advisory)
Frequently asked questions
- What is CVE-2026-90553?
- CVE-2026-90553 is a high-severity vulnerability in Vllm, classified under Code Injection. CVSS score: 7.8/10. Published 2026-09-12.
- How severe is CVE-2026-90553?
- High severity. CVSS v3 base score is 7.8 out of 10.