![CVE-2026-56340: vLLM - Denial of Service via Unvalidated Multimodal Embeddings [HIGH] CVSS 8.8 Exploit Intelligence — Recent CVEs / 8h 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 pro](https://exploit-intel.com/static/brand/og-default.png)
Back exploit-intel.com CVE-2026-56340: vLLM - Denial of Service via Unvalidated Multimodal Embeddings [HIGH] CVSS 8.8 Exploit Intelligence — Recent CVEs / 8h 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 pro
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.
The full story
This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.
