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.
CVSS breakdown
CVSS 4.0
Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
Low
User Interaction
None
Confidentiality (Vulnerable System)
High
Integrity (Vulnerable System)
High
Availability (Vulnerable System)
High
Confidentiality (Subsequent System)
None
Integrity (Subsequent System)
None
Availability (Subsequent System)
None
CVSS 3.1
Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High
Affected products
- vllm / vllm0.10.2 – 0.13.0
- vllm / vllm0.13.0 – 0.13.0