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.
{
"cna_assigner": "@huntr_ai",
"cwe_ids": [
"CWE-400"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/5xxx/CVE-2026-5497.json"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0.8.0"
},
{
"fixed": "0.19.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "58ee61422169ce17e08248f8efa1e9df434fe395"
}
],
"source": "REFERENCES_COMMIT"
}
]
}