{"id":"CVE-2026-56340","aliases":["GHSA-mcmc-2m55-j8jj","PYSEC-2026-250"],"url":"https://o3.security/vulnerability/CVE-2026-56340","summary":"vLLM - Denial of Service via Unvalidated Multimodal Embeddings","details":"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.","published":"2026-06-20T18:27:10.148Z","modified":"2026-08-12T03:51:47.690231517Z","cvss":null,"epss":null,"cisaKev":null,"exploitsKnown":0,"affectedPackages":[{"ecosystem":"PyPI","name":"vllm","fixedVersion":"0.13.0"}],"fix":null,"references":[{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-56340.json"},{"type":"ADVISORY","url":"https://access.redhat.com/security/cve/CVE-2026-56340"},{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/56xxx/CVE-2026-56340.json"},{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jj"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-56340"},{"type":"ADVISORY","url":"https://www.vulncheck.com/advisories/vllm-denial-of-service-via-unvalidated-multimodal-embeddings"},{"type":"REPORT","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2491060"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-08-12T03:51:47.690231517Z"}}