CVE-2026-56340
vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor …
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 now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jj
- www.vulncheck.com/advisories/vllm-denial-of-service-via-unvalidated-multimodal-embeddings
- access.redhat.com/security/cve/CVE-2026-56340
- bugzilla.redhat.com/show_bug.cgi?id=2491060
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-56340.json
- github.com/vllm-project/vllm/pull/30649
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-250.yaml
- github.com/advisories/GHSA-mcmc-2m55-j8jj
- nvd.nist.gov/vuln/detail/CVE-2026-56340
- cve.org/CVERecord?id=CVE-2026-56340
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.