vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-400"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/48xxx/CVE-2025-48956.json"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0.1.0"
},
{
"fixed": "0.10.1.1"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "d8b736f913a59117803d6701521d2e4861701944"
}
],
"source": "REFERENCES_COMMIT"
}
]
}