| Component | vLLM |
| Severity | high (CVSS 8.8) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
| Published (NVD) | 2026-06-20 |
| Last modified | 2026-07-15 |
| Affected versions | vllm >= 0.10.2, < 0.13.0 |
| Fixed in | 0.13.0 |
| Weakness | CWE-20CWE-787 |
| CISA KEV | not listed |
NVD 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.
What to do
- Upgrade vLLM to
0.13.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-56340
- https://github.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jj
- https://www.vulncheck.com/advisories/vllm-denial-of-service-via-unvalidated-multimodal-embeddings
- 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
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...