{"id":"CVE-2026-5497","title":"vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method","summary":"vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method …","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 >= 0.8.0, < 0.19.0"],"patched":["vllm 0.19.0"],"published":"2026-06-11","updated":"2026-07-03","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-5497","references":[{"url":"https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395","label":"security@huntr.dev"},{"url":"https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4","label":"security@huntr.dev"},{"url":"https://access.redhat.com/security/cve/CVE-2026-5497","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2487813","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4","label":"134c704f-9b21-4f2e-91b3-4a467353bcc0"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-5497"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-5497"},{"url":"https://access.redhat.com/errata/RHSA-2026:69466"},{"url":"https://access.redhat.com/errata/RHSA-2026:69467"},{"url":"https://access.redhat.com/errata/RHSA-2026:69469"},{"url":"https://access.redhat.com/errata/RHSA-2026:69464"}],"tags":["nvd","csaf","vex","red-hat"],"epss":0.00537,"epssPercentile":0.43963,"ingestedAt":"2026-07-03T14:03:37.086Z","slug":"CVE-2026-5497","body":"## Overview\n\nvLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.\n\n## Affected\n\n- `vllm >= 0.8.0, < 0.19.0`\n\n## Remediation\n\nUpgrade past the affected range:\n\n- `vllm 0.19.0`\n\n## Vendor advisories\n\n- **RHSA-2026:69466** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-21 · [advisory](https://access.redhat.com/errata/RHSA-2026:69466)\n- **RHSA-2026:69467** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-21 · [advisory](https://access.redhat.com/errata/RHSA-2026:69467)\n- **RHSA-2026:69469** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-21 · [advisory](https://access.redhat.com/errata/RHSA-2026:69469)\n- **RHSA-2026:69464** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-21 · [advisory](https://access.redhat.com/errata/RHSA-2026:69464)\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 2026-09-21 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json)","depth":"twilight","depthScore":41,"depthScoreParts":{"impact":41.3,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}