CVE-2026-56340
HIGH severity · CVSS 8.8 · Improper input validation
8.8CVSS HIGH
Summary
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.
Impact & exploitability
Attack vectorNetwork
Attack complexityLow
Privileges requiredLow
User interactionNone
Confidentiality impactHigh
Integrity impactHigh
Availability impactHigh
Exploit probability (EPSS)1%
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Affected products we track (1)
Recommendation
Apply the vendor fix promptly. Open any affected product above for its exact safe version.
Additional information
- NVD record
- https://github.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jjAdvisory
- https://www.vulncheck.com/advisories/vllm-denial-of-service-via-unvalidated-multimodal-embeddingsAdvisory
- https://access.redhat.com/security/cve/CVE-2026-56340
- https://bugzilla.redhat.com/show_bug.cgi?id=2491060
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-56340.json