vLLM - Denial of Service via Unvalidated Multimodal Embeddings
En bref
Sévérité
HIGH 8.7
EPSS
EPSS 0.64 % · centile 51 (2026-10-27)
État
PUBLISHED
Publiée
Mise à jour
Attribuée par
VulnCheck
Statut NVD
Modified
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.
