Buffer overflow in Vllm
CVE-2026-56340
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.
Vulnerability class: Drupalgeddon 2 (CVE-2018-7600)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 8.8 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.006, 51.5th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Vllm — versions 0.10.2, 0.13.0
Weakness classification (CWE)
References
- GitHub Security Advisory (GHSA-mcmc-2m55-j8jj) (vendor-advisory, Vendor Advisory)
- VulnCheck Advisory: vLLM - Denial of Service via Unvalidated Multimodal Embeddings (Third Party Advisory, third-party-advisory)
- access.redhat.com/security/cve/CVE-2026-56340
- bugzilla.redhat.com/show_bug.cgi
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-56340.json