NVD Vulnerability Detail
Search Exploit, PoC
CVE-2026-56340
Summary

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.

Publication Date June 21, 2026, 4:16 a.m.
Registration Date June 27, 2026, 4:07 a.m.
Last Update June 25, 2026, 2:17 a.m.
CVSS3.1 : HIGH
スコア 8.8
Vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
攻撃元区分(AV) ネットワーク
攻撃条件の複雑さ(AC)
攻撃に必要な特権レベル(PR)
利用者の関与(UI) 不要
影響の想定範囲(S) 変更なし
機密性への影響(C)
完全性への影響(I)
可用性への影響(A)
Related information, measures and tools
Common Vulnerabilities List