Yüksek CVSS 7.5 PoC var
CVE-2026-41523: Vllm: kod enjeksiyonu
Açıklama (NVD)
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.
Özet bilgiler
- Ürün
- Vllm Vllm
- CVSS v3.1
- 7.5
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H - EPSS
- %0,91 (yüzdelik 60)
- CWE
- CWE-94
- Yama
- Mevcut
Etkilenen sürümler
| Ürün | Başlangıç | Bitiş | Düzeltildi |
|---|---|---|---|
| vllm-vllm | — | — | 0.22.0 |
Kaynaklar
- NVD kaydı
- github.com
- github.com
- huntr.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- access.redhat.com
- bugzilla.redhat.com
- security.access.redhat.com
- CWE-94