{"id":"CVE-2026-114052","title":"vllm: vLLM: Denial of Service via unbounded processor caching in MOSS-Audio (CVE-2026-114052)","summary":"A flaw was found in vLLM. This vulnerability allows an unauthenticated remote attacker to cause a Denial of Service (DoS) via memory exhaustion. When serving MOSS-Audio models, the unauthenticated tokenize endpoint caches processor configu…","severity":"high","cvss":7.5,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","cvssSource":"vendor","cwe":"CWE-770","vendor":"Red Hat","product":"Red Hat AI Inference Server","affected":["ai_inference_server","enterprise_linux_ai_rhel_ai 3","openshift_ai_rhoai"],"published":"2026-10-21","updated":"2026-10-22","sourceUpdated":"2026-10-22T22:11:09+00:00","source":"CSAF","sourceUrl":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-114052.json","references":[{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-114052.json"},{"url":"https://access.redhat.com/security/cve/CVE-2026-114052"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2558036"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-114052"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-114052"},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-823j-m4cj-hmjf"},{"url":"https://www.vulncheck.com/advisories/vllm-0.25.0-before-0.31.0-moss-audio-memory-exhaustion-via-tokenize-mm-processor-kwargs"}],"tags":["csaf","vex","red-hat","cve.org"],"epss":0.00479,"epssPercentile":0.41141,"ssvc":{"exploitation":"none","automatable":"yes","technicalImpact":"partial","timestamp":"2026-10-22T18:16:43.778221Z"},"ingestedAt":"2026-10-21T01:37:08.043Z","slug":"CVE-2026-114052","body":"## Overview\n\nA flaw was found in vLLM. This vulnerability allows an unauthenticated remote attacker to cause a Denial of Service (DoS) via memory exhaustion. When serving MOSS-Audio models, the unauthenticated tokenize endpoint caches processor configurations in an unbounded cache. By submitting requests with distinct or oversized processor parameters, an attacker can exhaust system memory and crash the service.\n\n## Vendor advisories\n\n- **Red Hat VEX** · Important · affected: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · no fix planned: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · updated 2026-10-22 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-114052.json)\n\n**vllm: vLLM: Denial of Service via unbounded processor caching in MOSS-Audio** — rated Important by Red Hat. Released 2026-10-21, updated 2026-10-22.\n\nAffected:\n\n- Red Hat AI Inference Server\n- Red Hat Enterprise Linux AI (RHEL AI) 3\n- Red Hat OpenShift AI (RHOAI)\n\nNo fix planned:\n\n- Red Hat AI Inference Server\n- Red Hat Enterprise Linux AI (RHEL AI) 3\n- Red Hat OpenShift AI (RHOAI)\n\nNot affected:\n\n- Red Hat OpenShift AI (RHOAI)\n\n## Remediation\n\nAffected","depth":"twilight","depthScore":41,"depthScoreParts":{"impact":41.3,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}