Summary
Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Informationen offenzulegen, und um einen Denial of Service Angriff durchzuführen.
Product
Open Source vLLM ist eine Open-Source-Bibliothek für schnelle und effiziente Inferenz von Large Language Models (LLMs).
Vulnerabilities 2
-
Medium 5.3
vLLM: Cross-User Data Leak Vulnerability
vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the sa…
-
Medium 5.3
vLLM before 0.27.0 Denial of Service via DeepStream Backend
vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video t…
Revision history
-
#4
Neue Updates von Red Hat aufgenommen
-
#3
Neue Updates von Red Hat aufgenommen
-
#2
CVE-Nummern ergänzt
-
#1
Initiale Fassung
References
-
GitHub Security Advisory GHSA-7m6h-x95x-82q5 vom 2026-08-10
https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5
-
GitHub Security Advisory GHSA-cqm8-jxg6-fqfq vom 2026-08-10
https://github.com/vllm-project/vllm/security/advisories/GHSA-cqm8-jxg6-fqfq
-
Red Hat Security Advisory RHSA-2026:82061 vom 2026-10-13
https://access.redhat.com/errata/RHSA-2026:82061
-
Red Hat Security Advisory RHSA-2026:82059 vom 2026-10-13
https://access.redhat.com/errata/RHSA-2026:82059
-
Red Hat Security Advisory RHSA-2026:92449 vom 2026-10-29
https://access.redhat.com/errata/RHSA-2026:92449
-
Red Hat Security Advisory RHSA-2026:92452 vom 2026-10-29
https://access.redhat.com/errata/RHSA-2026:92452