vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to ~14.9GB of float32 PCM at decode time. This vulnerability is fixed in 0.23.1rc0.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-409"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/54xxx/CVE-2026-54233.json"
}{
"extracted_events": [
{
"range": [
{
"introduced": "0"
},
{
"fixed": "0.23.1rc0"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StringRangeExpression"
},
{
"range": [
{
"introduced": "0"
},
{
"fixed": "0.23.1rc0"
}
],
"source": "DESCRIPTION"
}
]
}