{"id":"CVE-2026-37237","title":"vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion","summary":"vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetch_audio and AsyncMediaIO.fetch_image functions in multimodal/inputs.py fetch user-supplied media URLs using …","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","cwe":["CWE-400","CWE-770"],"vendor":"vllm","product":"vllm","affected":["vllm <= 0.17.0"],"published":"2026-08-28","updated":"2026-09-29","sourceUpdated":"2026-09-29T12:52:25.210","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-37237","references":[{"url":"https://github.com/vllm-project/vllm/blob/main/vllm/multimodal/inputs.py","label":"cve@mitre.org"},{"url":"https://github.com/vllm-project/vllm/pull/36506","label":"cve@mitre.org"},{"url":"https://s00me00ne.com/cve/cve-2026-37237/","label":"cve@mitre.org"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-37237.json"},{"url":"https://access.redhat.com/security/cve/CVE-2026-37237"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2525629"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-37237"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-37237"},{"url":"https://access.redhat.com/errata/RHSA-2026:73929"},{"url":"https://access.redhat.com/errata/RHSA-2026:73930"},{"url":"https://access.redhat.com/errata/RHSA-2026:83112"},{"url":"https://access.redhat.com/errata/RHSA-2026:83120"},{"url":"https://access.redhat.com/errata/RHSA-2026:83121"},{"url":"https://access.redhat.com/errata/RHSA-2026:83114"},{"url":"https://access.redhat.com/errata/RHSA-2026:84734"}],"tags":["nvd","csaf","vex","red-hat"],"ingestedAt":"2026-09-09T16:14:05.517Z","epss":0.00727,"epssPercentile":0.53938,"patched":["ai_inference_server 3.2"],"slug":"CVE-2026-37237","body":"## Overview\n\nvLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetch_audio and AsyncMediaIO.fetch_image functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read() without enforcing a maximum response size, allowing an attacker to exhaust server memory by providing a URL to an arbitrarily large file.\n\n## Affected\n\n- `vllm <= 0.17.0`\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.\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 2026-10-19 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-37237.json)\n- **RHSA-2026:73929** · Red Hat · fixed in: Red Hat AI Inference Server 3.2 · released 2026-09-30 · [advisory](https://access.redhat.com/errata/RHSA-2026:73929)\n- **RHSA-2026:73930** · Red Hat · fixed in: Red Hat AI Inference Server 3.2 · released 2026-09-30 · [advisory](https://access.redhat.com/errata/RHSA-2026:73930)\n- **RHSA-2026:83112** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-10-14 · [advisory](https://access.redhat.com/errata/RHSA-2026:83112)\n- **RHSA-2026:83120** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-10-14 · [advisory](https://access.redhat.com/errata/RHSA-2026:83120)\n- **RHSA-2026:83121** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-10-14 · [advisory](https://access.redhat.com/errata/RHSA-2026:83121)\n- **RHSA-2026:83114** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-10-14 · [advisory](https://access.redhat.com/errata/RHSA-2026:83114)\n- **RHSA-2026:84734** · Red Hat · fixed in: Red Hat OpenShift AI 3.4 · released 2026-10-19 · [advisory](https://access.redhat.com/errata/RHSA-2026:84734)","depth":"twilight","depthScore":41,"depthScoreParts":{"impact":41.3,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}