{"vulnerability": "CVE-2024-8939", "sightings": [{"uuid": "d8caa0c1-9db1-4dca-af8a-b323eb9953eb", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "CVE-2024-8939", "type": "seen", "source": "https://t.me/cvedetector/5819", "content": "{\n  \"Source\": \"CVE FEED\",\n  \"Title\": \"CVE-2024-8939 - ilab Model Serve Denial of Service Vulnerability\", \n  \"Content\": \"CVE ID : CVE-2024-8939 \nPublished : Sept. 17, 2024, 5:15 p.m. | 24\u00a0minutes ago \nDescription : 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. \nSeverity: 6.2 | MEDIUM \nVisit the link for more details, such as CVSS details, affected products, timeline, and more...\",\n  \"Detection Date\": \"17 Sep 2024\",\n  \"Type\": \"Vulnerability\"\n}\n\ud83d\udd39 t.me/cvedetector \ud83d\udd39", "creation_timestamp": "2024-09-17T19:47:23.000000Z"}, {"uuid": "b9bbf636-2b71-4552-bffd-537f838b1a75", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "CVE-2024-8939", "type": "seen", "source": "https://t.me/DarkWebInformer_CVEAlerts/1466", "content": "\ud83d\udd17 DarkWebInformer.com - Cyber Threat Intelligence\n\ud83d\udccc CVE ID: CVE-2024-8939\n\ud83d\udd39 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.\n\ud83d\udccf Published: 2024-09-17T16:21:15.222Z\n\ud83d\udccf Modified: 2025-01-14T08:28:57.142Z\n\ud83d\udd17 References:\n1. https://access.redhat.com/security/cve/CVE-2024-8939\n2. https://bugzilla.redhat.com/show_bug.cgi?id=2312782", "creation_timestamp": "2025-01-14T09:10:38.000000Z"}]}