CVE-2026-105753

Katalog CVE

CVSS 6.5 · Medium EPSS 0,43%

Kerentanan Reachable Assertion pada vllm. Skor CVSS 3.1 6.5 (Medium) menurut github.com.

Deskripsi (NVD)

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal rendering and before engine admission, while the engine receiver cache never receives the payload if that request is rejected. A later request reusing the same media hash causes MultiModalProcessorSenderCache to send no payload and MultiModalReceiverCache to reach an assertion with the message "Expected a cached item," producing a shared-service availability failure. This issue is fixed in version 0.28.0.

Rincian

Terbit di NVD

5 Oktober 2026

Terakhir diubah

8 Oktober 2026

Status NVD

Analyzed

CVSS 3.1

6.5 (Medium), sumber github.com
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H · uraikan di kalkulator

Jenis kelemahan (CWE)

CWE-617: Reachable Assertion

EPSS (30 hari)

0,43% peluang dieksploitasi; lebih tinggi dari 35,2% CVE lain

Produk dan versi terdampak

> Data dari konfigurasi CPE di NVD.

Referensi dan perbaikan

• https://github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84f mitigasi · advisory vendor
• https://github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9 patch
• https://github.com/vllm-project/vllm/pull/46747 issue tracking · patch
• https://github.com/vllm-project/vllm/pull/51897 issue tracking · patch
• https://github.com/vllm-project/vllm/releases/tag/v0.28.0 release notes