CVE-2026-56340

June 20, 2026, 7:16 p.m.

8.7
High

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.

Product(s) Impacted

Vendor Product Versions
Vllm
  • Vllm
  • 0.10.2-0.13.0
Pytorch
  • Pytorch
  • *

Weaknesses

Common security weaknesses mapped to this vulnerability.

CWE-20
Improper Input Validation
The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.

*CPE(s)

Affected systems and software identified for this CVE.

Type Vendor Product Version Update Edition Language Software Edition Target Software Target Hardware Other Information
a vllm vllm 0.10.2-0.13.0 / / / / / / /
a pytorch pytorch / / / / / / / /

CVSS Score

8.7 / 10

CVSS Data - 4.0

  • Attack Vector: NETWORK
  • Attack Complexity: LOW
  • Attack Requirements: NONE
  • Privileges Required: LOW
  • User Interaction: NONE
  • Scope:
  • Confidentiality Impact: HIGH
  • Integrity Impact: HIGH
  • Availability Impact: HIGH
  • Exploit Maturity: NOT_DEFINED
  • 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

    View Vector String

Timeline

Published: June 20, 2026, 7:16 p.m.
Last Modified: June 20, 2026, 7:16 p.m.

Status : Received

CVE has been recently published to the CVE List and has been received by the NVD.

More info

*Disclaimer: Some vulnerabilities do not have an associated CPE. To enhance the data, we use AI to infer CPEs based on CVE details. This is an automated process and might not always be accurate.