CVE Professor — Güvenlik Açığı Takip & Analiz
›
CVE-2026-100651

CWE-400

ORTA CVSS 6.5 ⚡ EPSS 0.4% NVD

vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' (multimodal) payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied token_ids, and GenerateRequest.token_ids (vllm/entrypoints/serve/disagg/protocol.py) is not checked against model_config.max_model_len. For multimodal processors that report skip_prompt_length_check=True (for example Nemotron Parse, Whisper, and FireRedLID), InputProcessor._validate_prompt_len() returns immediately for both encoder and decoder prompts, so an overlong prompt becomes an EngineCoreRequest and reaches the worker input-batch copy into a fixed max_model_len-wide NumPy row. A client able to reach the endpoint on an affected model configuration can therefore submit an overlong token_ids list to trigger a worker failure and denial of service. Fixed in 0.29.0.

Yayınlanma 26.09.2026
ISO Tarih 2026-09-26
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
0.4%
30 günlük olasılık
Tüm CVElerin 33. yüzdeliğinde — Bu açığın istismar edilme ihtimali çoğu CVEden yüksek.
AI Güvenlik Analizi

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CVE-2026-100651
CVSS 6.5/10 · ORTA · 26.09.2026
CWE: CWE-400
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🎯 AÇIK NEDİR?
Açıklama: vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' (multimodal) payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied token_ids, and GenerateRequest.token_ids (vllm/entrypoints/serve/disagg/protocol.py) is not checke…
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-400
Etkilenen Ürünler (1)
vllm:vllm (tüm sürümler)
Referanslar (3)
github.com exploit advisory
github.com exploit advisory
İlgili CVE'ler
9.9
CVE-2026-101501
Vulnerability in Oracle Trusted Answer Search (component: PLSQL package). The supported version that is affe
9.8
CVE-2026-33971
In the LTE RRC component, improper handling of messages before authentication triggers a data abort, which lea
9.3
CVE-2026-51106
An issue in TokTok qTox v1.18.4 allows a local attacker to cause a denial of service via the src/persistence/s
9.1
CVE-2026-74841
In multitenant deployments, ContextFilter and LoginWorker built a per-tenant delegator name from a request-sup
9.1
CVE-2026-111108
Apache Kafka's code-generated protocol readers pre-size an array's collection from the element count declared