vllm-project · vLLM · published 2025-11-21
CVE-2025-62372vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs
Routine No exploitation evidence; EPSS 0.4%.
CVE-2025-62372 is not known to be exploited in the wild. EPSS estimates a 0.4% chance of exploitation in the next 30 days, higher than 36% of all CVEs. This vLLM vulnerability: CVSS 8.3 (v4.0). Fixed upstream in vLLM 0.14.0. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.14.0.
Patch events
AI toolingvLLM
vLLM security release: 0.14.0
Upgrade to
0.14.0Why: Vendor security release for server software (most severe: CVE-2026-22807).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.4% (36th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 8.3 (v4.0)CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
>= 0.5.5, < 0.11.1(affected)
Description (from the CVE record)#
vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.
Quoted from the CVE Program record.