{"id":"CVE-2024-8939","aliases":["EUVD-2024-2887","GHSA-wc36-9694-f9rf","PYSEC-2026-2025"],"status":"published","title":"Vllm: denials of service in vllm json web api","description":"A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.","severity":{"version":"3.1","score":6.2,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-11","score":0.00233,"percentile":0.14317,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-400"],"published":"2024-09-17T16:21:15Z","modified":"2026-10-28T02:30:56Z","affected":[{"source":"ghsa","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"0.5.0.post1"}]}]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"0.5.0.post1"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1"]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"0.5.0.post1"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1"]}],"products":[{"vendor":"red hat","product":"red hat enterprise linux ai (rhel ai)"}],"references":[{"url":"https://access.redhat.com/security/cve/CVE-2024-8939","tags":["vdb-entry","x_refsource_REDHAT","advisory","web"]},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2312782","tags":["issue-tracking","x_refsource_REDHAT","report","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2024-8939","tags":["advisory"]},{"url":"https://github.com/vllm-project/vllm/issues/6137","tags":["web"]},{"url":"https://github.com/advisories/GHSA-wc36-9694-f9rf","tags":["advisory"]},{"url":"https://access.redhat.com/downloads/content/package-browser/","tags":["web"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2024/8xxx/CVE-2024-8939.json","tags":["advisory"]},{"url":"https://github.com/vllm-project/vllm","tags":["package"]},{"url":"https://pypi.org/project/vllm","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2024-8939","title":"Vllm: denials of service in vllm json web api","description":"A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.","status":"published","published":"2024-09-17T16:21:15.222Z","modified":"2025-11-20T20:57:47.098Z","cvss":[{"version":"3.1","score":6.2,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"cna"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T14:34:08.843708Z"}],"euvd":[{"id":"EUVD-2024-2887","description":"A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.","status":"published","published":"2024-09-17T16:21:15Z","modified":"2025-11-20T20:57:47Z","cvss":[{"version":"3.1","score":6.2,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T19:49:14.058235Z"}],"ghsa":[{"id":"GHSA-wc36-9694-f9rf","title":"vLLM Denial of Service via the best_of parameter","description":"A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.","status":"published","published":"2024-09-17T18:33:26Z","modified":"2024-09-17T21:56:56Z","cvss":[{"version":"4.0","score":6.9,"vector":"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","level":"medium"},{"version":"3.1","score":6.2,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T14:38:03.800952Z"}],"nvd":[{"id":"CVE-2024-8939","description":"A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.","status":"published","published":"2024-09-17T17:15:11.327Z","modified":"2026-06-17T08:23:35.693Z","cvss":[{"version":"3.1","score":6.2,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"secondary"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T14:10:26.717759Z"}],"osv":[{"id":"CVE-2024-8939","title":"Vllm: denials of service in vllm json web api","description":"A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.","status":"published","published":"2024-09-17T16:21:15.222Z","modified":"2026-10-28T02:30:56.149140308Z","cvss":[{"version":"3.1","score":6.2,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T15:44:45.712478Z"},{"id":"GHSA-wc36-9694-f9rf","title":"vLLM Denial of Service via the best_of parameter","description":"A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.","status":"published","published":"2024-09-17T18:33:26Z","modified":"2026-08-07T08:12:14.649360369Z","cvss":[{"version":"3.1","score":6.2,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"medium"},{"version":"4.0","score":6.9,"vector":"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","level":"medium"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T15:46:58.401149Z"},{"id":"PYSEC-2026-2025","title":"vLLM Denial of Service via the best_of parameter","description":"A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.","status":"published","published":"2026-07-07T14:34:41.654363Z","modified":"2026-07-07T17:48:17.622518271Z","cvss":[{"version":"3.1","score":6.2,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"medium"},{"version":"4.0","score":6.9,"vector":"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","level":"medium"}],"updated_at":"2026-11-02T15:52:55.537808Z"}]}}