vllm-project · vLLM · published 2026-09-12
CVE-2026-90553vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor
Routine No exploitation evidence; EPSS 0.3%.
CVE-2026-90553 is not known to be exploited in the wild. EPSS estimates a 0.3% chance of exploitation in the next 30 days, higher than 24% of all CVEs. This vLLM vulnerability: CVSS 8.5 (v4.0), a successful attack gives total control of the component. Fixed upstream in vLLM 0.28.0. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.28.0.
Patch events
AI toolingvLLM
vLLM security release: 0.28.0
Upgrade to
0.28.0Why: CVE-2026-69147: Public proof-of-concept exists (SSVC exploitation: poc).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.3% (24th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 8.5 (v4.0)CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | total | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vLLM
0to before0.28.0(affected)0.28.0(unaffected)
Description (from the CVE record)#
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.
Quoted from the CVE Program record.