{"id":"CVE-2025-62426","title":"vllm: vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs` (CVE-2025-624…","summary":"A vulnerability in vLLM allows an authenticated user to trigger unintended tokenization during chat template processing by supplying crafted chat_template_kwargs to the /v1/chat/completions or /tokenize endpoints. By forcing the server to …","severity":"medium","cvss":6.5,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","cvssSource":"vendor","cwe":"CWE-770","vendor":"Red Hat","product":"Red Hat Enterprise Linux AI (RHEL AI)","affected":["ai_inference_server","enterprise_linux_ai_rhel_ai","enterprise_linux_ai_rhel_ai 3","openshift_ai_rhoai","ai_inference_server 3.2"],"patched":["ai_inference_server 3.2"],"published":"2025-11-21","updated":"2026-09-21","sourceUpdated":"2026-09-21T17:09:31+00:00","source":"CSAF","sourceUrl":"https://security.access.redhat.com/data/csaf/v2/vex/2025/cve-2025-62426.json","references":[{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2025/cve-2025-62426.json"},{"url":"https://access.redhat.com/security/cve/CVE-2025-62426"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2416278"},{"url":"https://www.cve.org/CVERecord?id=CVE-2025-62426"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2025-62426"},{"url":"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610"},{"url":"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814"},{"url":"https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b"},{"url":"https://github.com/vllm-project/vllm/pull/27205"},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p"},{"url":"https://access.redhat.com/errata/RHSA-2026:3461"},{"url":"https://access.redhat.com/errata/RHSA-2026:3462"},{"url":"https://github.com/advisories/GHSA-69j4-grxj-j64p"},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2012.yaml"},{"url":"https://github.com/vllm-project/vllm"},{"url":"https://pypi.org/project/vllm"}],"tags":["csaf","vex","red-hat","osv","pip"],"epss":0.00368,"epssPercentile":0.27871,"aliases":["GHSA-69j4-grxj-j64p","PYSEC-2026-2012"],"ecosystem":"pip","ingestedAt":"2026-07-08T18:25:46.322Z","slug":"CVE-2025-62426","body":"## Overview\n\nA vulnerability in vLLM allows an authenticated user to trigger unintended tokenization during chat template processing by supplying crafted chat_template_kwargs to the /v1/chat/completions or /tokenize endpoints. By forcing the server to tokenize very large inputs, an attacker can block the API server’s event loop for extended periods, causing a denial of service and delaying all other requests.\n\n## Vendor advisories\n\n- **RHSA-2026:3461** · Red Hat · fixed in: Red Hat AI Inference Server 3.2 · released 2026-02-27 · [advisory](https://access.redhat.com/errata/RHSA-2026:3461)\n- **RHSA-2026:3462** · Red Hat · fixed in: Red Hat AI Inference Server 3.2 · released 2026-02-27 · [advisory](https://access.redhat.com/errata/RHSA-2026:3462)\n- **Red Hat VEX** · Moderate · affected: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI), 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), Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · updated 2026-09-21 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2025/cve-2025-62426.json)\n\n**vllm: vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`** — rated Moderate by Red Hat. Released 2025-11-21, updated 2026-09-21.\n\nAffected:\n\n- Red Hat AI Inference Server\n- Red Hat Enterprise Linux AI (RHEL AI)\n- Red Hat Enterprise Linux AI (RHEL AI) 3\n- Red Hat OpenShift AI (RHOAI)\n\nFixed:\n\n- Red Hat AI Inference Server 3.2\n\nNo fix planned:\n\n- Red Hat AI Inference Server\n- Red Hat Enterprise Linux AI (RHEL AI)\n- Red Hat Enterprise Linux AI (RHEL AI) 3\n- Red Hat OpenShift AI (RHOAI)\n\n## Remediation\n\nFor more information visit https://access.redhat.com/errata/RHSA-2026:3461 https://access.redhat.com/errata/RHSA-2026:3461\nFor more information visit https://access.redhat.com/errata/RHSA-2026:3462 https://access.redhat.com/errata/RHSA-2026:3462\n\nWorkarounds / mitigations:\n\n- No mitigation is currently available that meets Red Hat Product Security’s standards for usability, deployment, applicability, or stability.\n\n## Package advisory (CVE-2025-62426)\n\nAffected packages:\n\n- `vllm >= 0.5.5, < 0.11.1`\n\nPatched in:\n\n- `vllm 0.11.1`\n\nSource: https://osv.dev/vulnerability/GHSA-69j4-grxj-j64p","depth":"sunlit","depthScore":36,"depthScoreParts":{"impact":35.8,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}