CVE Professor — Güvenlik Açığı Takip & Analiz
›
CVE-2026-105754

CWE-20 · CWE-617 · CWE-639

ORTA CVSS 6.5 ⚡ EPSS 0.3% NVD

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.

Yayınlanma 05.10.2026
ISO Tarih 2026-10-05
CVSS Sürüm v3.1
Kaynak NVD
CVSS v3.1 Metrikleri
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Attack Vector Network AV:N
Attack Complexity Low AC:L
Privileges Req. Low PR:L
User Interaction None UI:N
Scope Unchanged S:U
Confidentiality None C:N
Integrity None I:N
Availability High A:H
EPSS — Exploit Olasılık Skoru
0.3%
30 günlük olasılık
Tüm CVElerin 19. yüzdeliğinde — Bu açığın istismar edilme ihtimali çoğu CVEden yüksek.
AI Güvenlik Analizi

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CVE-2026-105754
CVSS 6.5/10 · ORTA · 05.10.2026
CWE: CWE-20, CWE-617
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🎯 AÇIK NEDİR?
Açıklama: vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the a…
Etkilenen: vllm:vllm

⚡ SALDIRI ZİNCİRİ
İnternet üzerinden uzaktan | düşük yetkili hesap | kullanıcı etkileşimi YOK | düşük karmaşıklık.

🌍 GERÇEK DÜNYA ETKİSİ
Hizmet tamamen devre dışı bırakılabilir.

🛡️ ÇÖZÜM VE MİTİGASYON
→ vllm:vllm için üretici güvenlik güncellemesini uygula.
→ WAF kuralı ekle, anormal trafik için IDS alert oluştur.

⚠️ ACİLİYET
📋 Rutin güncelleme (30 gün)

────────────────────────────────────────
[Kural Tabanlı Analiz] [💡 config.json dosyasına ai_key (Claude: sk-ant-... veya Groq: gsk_...) ekleyerek gerçek AI analizi kullanabilirsiniz]

[⚠️ AI key mevcut ancak istek başarısız — kural tabanlı analiz kullanıldı]

Hedef Keşif Sorguları

FOFA Sorgusu

app="vllm vllm"
CVSS Skoru
6.5 / 10 · CVSS ORTA
Zayıflık Türleri (CWE)
CWE-20 CWE-617 CWE-639 CWE-668 CWE-704 CWE-1284
Etkilenen Ürünler (1)
vllm:vllm (tüm sürümler)
Referanslar (4)
github.com patch
github.com patch
github.com advisory
İlgili CVE'ler
10.0
CVE-2026-53998
Phoenix is an AI observability and evaluation platform. From 13.0.0 until 15.7.0, the applyChatTemplate GraphQ
10.0
CVE-2026-123551
OpenAM from 14.0.0 before 16.1.4 contains an information disclosure vulnerability that allows unauthenticated
10.0
CVE-2026-109469
Authorization bypass through user-controlled key in Entra Device Registration allows an unauthorized attacker
10.0
CVE-2026-87337
Vulnerability in the Oracle Access Manager product of Oracle Fusion Middleware (component: Authentication Engi
10.0
CVE-2024-34323
ProPhoenix Law RMS v2022.2403.3.101 was discovered to contain an Insecure Direct Object Reference (IDOR) via t