CVE-2026-56340

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.
Configurations

Configuration 1 (hide)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

History

30 Jun 2026, 03:21

Type Values Removed Values Added
CWE CWE-787
References
  • () https://access.redhat.com/security/cve/CVE-2026-56340 -
  • () https://bugzilla.redhat.com/show_bug.cgi?id=2491060 -
  • () https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-56340.json -

26 Jun 2026, 20:29

Type Values Removed Values Added
CWE NVD-CWE-noinfo
CPE cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
References () https://github.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jj - () https://github.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jj - Vendor Advisory
References () https://www.vulncheck.com/advisories/vllm-denial-of-service-via-unvalidated-multimodal-embeddings - () https://www.vulncheck.com/advisories/vllm-denial-of-service-via-unvalidated-multimodal-embeddings - Third Party Advisory
First Time Vllm
Vllm vllm

20 Jun 2026, 19:16

Type Values Removed Values Added
New CVE

Information

Published : 2026-06-20 19:16

Updated : 2026-07-15 01:16


NVD link : CVE-2026-56340

Mitre link : CVE-2026-56340

CVE.ORG link : CVE-2026-56340


JSON object : View

Products Affected

vllm

  • vllm
CWE
CWE-20

Improper Input Validation

NVD-CWE-noinfo CWE-787

Out-of-bounds Write