6.2
Moyenne
CVE-2024-8939 A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the…
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.
Produits et versions touchés
| Produit | Versions touchées | Corrigé en |
|---|---|---|
| Red Hat Enterprise Linux AI (RHEL AI) | Versions non publiées |
Références
- access.redhat.com access.redhat.com
- RHBZ#2312782 bugzilla.redhat.com
Chronologie
- Publiée
- Dernière modification
Autres CVE de Red Hat Enterprise Linux AI (RHEL AI)
Les 6 CVE de Red Hat Enterprise Linux AI (RHEL AI) →
CVE-2025-6242
A Server-Side Request Forgery (SSRF) vulnerability exists in the MediaConnector class within the vLLM project's…
7.1
Élevée
CVE-2025-8556
A flaw was found in CIRCL's implementation of the FourQ elliptic curve
3.7
Faible
CVE-2024-11079
Ansible-core: unsafe tagging bypass via hostvars object in ansible-core
5.5
Moyenne
CVE-2024-8768
A flaw was found in the vLLM library
7.5
Élevée