Bug 2491060 (CVE-2026-56340) - CVE-2026-56340 vllm: vLLM: Denial of service and potential arbitrary code execution via malformed multimodal embedding requests
Summary: CVE-2026-56340 vllm: vLLM: Denial of service and potential arbitrary code exe...
Keywords:
Status: NEW
Alias: CVE-2026-56340
Product: Security Response
Classification: Other
Component: vulnerability
Version: unspecified
Hardware: All
OS: Linux
high
high
Target Milestone: ---
Assignee: Product Security DevOps Team
QA Contact:
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2026-06-20 19:01 UTC by OSIDB Bzimport
Modified: 2026-06-29 05:02 UTC (History)
7 users (show)

Fixed In Version:
Clone Of:
Environment:
Last Closed:
Embargoed:


Attachments (Terms of Use)

Description OSIDB Bzimport 2026-06-20 19:01:24 UTC
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.


Note You need to log in before you can comment on or make changes to this bug.