CVE-2026-5497

Source
https://cve.org/CVERecord?id=CVE-2026-5497
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-5497.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2026-5497
Published
2026-06-11T08:31:18.953Z
Modified
2026-07-08T08:09:54.504583102Z
Severity
  • 7.5 (High) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H CVSS Calculator
Summary
Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm
Details

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 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.

Database specific
{
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/5xxx/CVE-2026-5497.json",
    "cna_assigner": "@huntr_ai",
    "cwe_ids": [
        "CWE-400"
    ]
}
References

Affected packages

Git / github.com/vllm-project/vllm

Affected ranges

Type
GIT
Repo
https://github.com/vllm-project/vllm
Events
Database specific
{
    "source": [
        "CPE_RANGE",
        "REFERENCES"
    ],
    "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
    "extracted_events": [
        {
            "introduced": "0.8.0"
        },
        {
            "fixed": "0.19.0"
        }
    ]
}

Database specific

source
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-5497.json"