CVE-2026-56340

Description

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.

How to fix CVE-2026-56340

To remediate CVE-2026-56340, upgrade the affected package to a fixed version below.

• —upgrade to 0.13.0 or later
• —upgrade to 0.13.0 or later

Is CVE-2026-56340 being exploited?

Low — EPSS is 0.4%, meaning exploitation activity has not been observed at scale.

Affected packages (2)

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

CVSS scores

References (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