CVE-2026-56340
vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.64%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 4.0
- 8.7 HIGHCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
- EPSS
- 0.64% probability · 49th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-20, CWE-787
- Affected
- vllm/vllm
- Source
- disclosure@vulncheck.com
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jjVendor Advisory
- https://www.vulncheck.com/advisories/vllm-denial-of-service-via-unvalidated-multimodal-embeddingsThird Party Advisory
- 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
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.