CVE detail
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.
Buzz score
Why this CVE is surfacing
This all-time snapshot uses the same composite formula as Trending across a 30-year evidence window, rather than a current rolling window.
Buzz score components · mention 17.9 · diversity 14.5 · KEV 0.0 · OTX 0.0 · PoC 0.0
Why it matters now
Mention timeline
- Total mentions
- 0
- within the 30d window
- Peak daily
- 0
- highest bucket
Evidence
Source links by recency
5 source links · newest first
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-56340.jsonsecurity.access.redhat.com
No excerpt available.
Vendor Advisorysecurity.access.redhat.comJun 20, 2026, 7:16 PM - https://bugzilla.redhat.com/show_bug.cgi?id=2491060bugzilla.redhat.com
No excerpt available.
Exploitbugzilla.redhat.comJun 20, 2026, 7:16 PM - https://access.redhat.com/security/cve/CVE-2026-56340access.redhat.com
No excerpt available.
Vendor Advisoryaccess.redhat.comJun 20, 2026, 7:16 PM - https://www.vulncheck.com/advisories/vllm-denial-of-service-via-unvalidated-multimodal-embeddingswww.vulncheck.com
No excerpt available.
Exploitwww.vulncheck.comJun 20, 2026, 7:16 PM No excerpt available.
Exploitgithub.comJun 20, 2026, 7:16 PM
Exploit code
Public exploit repository references
Public PoC repositories are third-party, potentially unsafe artifacts. Treat their code as untrusted and use it only on authorized systems in an isolated, least-privilege environment. cvebuzz does not execute the code or verify that an exploit works.
0 repository references · best confidence N/A · max 0 stars
Related records
Similar CVEs
6 related CVEs with shared weakness or product evidence
- CVE-2025-62164CVSS 8.8 · High
vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of…
- CVE-2026-50144CVSS 7.1 · High
ncnn is a high-performance neural network inference framework optimized for the mobile platform. In commit e54f7b1f88434e1d844ea0551b880a1cfb079ce1 and earlier, ncnn allows an out…
- CVE-2026-14087CVSS 8.8 · High
Heap buffer overflow in WebNN in Google Chrome on Windows prior to 150.0.7871.47 allowed a remote attacker who had compromised the renderer process to potentially exploit heap cor…
- CVE-2026-45328CVSS 9.3 · Critical
ESF-IDF is the Espressif Internet of Things (IOT) Development Framework. In versions 5.5.4 and 6.0, the esp_tee component exposes secure-service wrappers in esp_secure_services.c…
- CVE-2026-49840CVSS 9.1 · Critical
FreeSWITCH is a Software Defined Telecom Stack enabling the digital transformation from proprietary telecom switches to a software implementation that runs on any commodity hardwa…
- CVE-2026-49475CVSS 7.5 · High
FreeSWITCH is a Software Defined Telecom Stack enabling the digital transformation from proprietary telecom switches to a software implementation that runs on any commodity hardwa…