Back to overview

CVE-2026-56340

HIGH
8.8
CVSS 3.1
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.

Metadata

CVE ID
CVE-2026-56340
State
PUBLISHED
Assigner
VulnCheck
Reserved
2026-06-20 13:13 UTC
Published
2026-06-20 18:27 UTC
Last updated
2026-06-20 18:27 UTC
Primary CWE
CWE-20
Improper Input Validation
Vendor / Product
vLLM / vLLM
Sources
cve.org  ·  NVD

Severity & Metrics

8.8 HIGH CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Affected products (1)
VendorProductPlatformVersions
vLLM vLLM 0.10.2 < 0.13.0, 0.13.0
Weakness (CWE)
CWESourceDescription
CWE-20 cna Improper Input Validation
CVSS scores (2)
ScoreSeverityVersionSourceVector
8.8 HIGH 3.1 cna CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
8.7 HIGH 4.0 cna CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
References (2)
Back to overview