Vulnerability · Published Jun 20, 2026 · Assigned by VulnCheck

CVE-2026-56340vLLM - Denial of Service via Unvalidated Multimodal Embeddings

High 8.8

In plain English

A high-severity improper input validation in vLLM from vLLM. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 51% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)8.8High

Exploit odds (30 days)0.6%top 48.9% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	vllm	0.13.0	GHSA-mcmc-2m55-j8jj
PyPI	vllm	0.13.0	PYSEC-2026-250

Affected products (as reported)

Vendor	Product	Versions
vLLM	vLLM	0.10.2 – before 0.13.0

Weakness: CWE-20, CWE-787 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

GHSA Advisory GHSA-mcmc-2m55-j8jj vendor-advisory
VulnCheck Advisory: vLLM - Denial of Service via Unvalidated Multimodal Embeddings third-party-advisory
https://access.redhat.com/security/cve/CVE-2026-56340 vdb-entry, x_refsource_REDHAT
RHBZ#2491060 issue-tracking, x_refsource_REDHAT
https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-56340.json x_sadp-csaf-vex