CVE-2026-56340

描述

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.

如何修補 CVE-2026-56340

要修補 CVE-2026-56340,請將受影響套件升級到下列已修補版本。

• —升級至 0.13.0 或更新版本
• —升級至 0.13.0 或更新版本

CVE-2026-56340 正在被利用嗎?

低 — EPSS 為 0.4%,目前沒有觀察到大規模利用活動。

受影響套件(2)

• >= 0.10.2, < 0.13.0
• >= 0.10.2, < 0.13.0

CVSS 分數

參考連結(4)

• ADVISORYwww.vulncheck.com/advisories/vllm-denial-of-service-via-unvalidated-multimodal-embeddings
• PATCHgithub.com/vllm-project/vllm
• WEBgithub.com/vllm-project/vllm/pull/30649
• WEBgithub.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jj