vllm-project · vLLM · published 2026-10-05
CVE-2026-105760vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion
Routine No exploitation evidence; EPSS 0.3%.
CVE-2026-105760 is not known to be exploited in the wild. EPSS estimates a 0.3% chance of exploitation in the next 30 days, higher than 22% of all CVEs. This vLLM vulnerability: CVSS 5.3 (v3.1), attacks can be automated. Fixed upstream in vLLM 0.30.0. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.30.0.
Patch events
AI toolingvLLM
vLLM security release: 0.30.0
Upgrade to
0.30.0Why: CVE-2026-105759: 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% (23th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 5.3 (v3.1)CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | Yes | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
>= 0.23.0rc2, < 0.30.0(affected)
Description (from the CVE record)#
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.
Quoted from the CVE Program record.