CVE-2026-56340
Published:June 20, 2026
Updated:August 04, 2026
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
vllm (CONDA):
Affected version(s) =0.10.2 <0.13.0Fix Suggestion:
Update to version 0.13.0vllm (PYTHON):
Affected version(s) >=0.10.2 <0.13.0Fix Suggestion:
Update to version 0.13.0Related Resources (9)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.7
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
LOW
User Interaction
NONE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
HIGH
Vulnerable System Availability
HIGH
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
8.8
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
HIGH
Integrity
HIGH
Availability
HIGH
Weakness Type (CWE)
EPSS
Base Score:
0.35