CVE Professor — Güvenlik Açığı Takip & Analiz
›
CVE-2026-57173

CWE-770

ORTA CVSS 6.5 ⚡ EPSS 0.7% NVD

vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM allocation, bypassing the duration guard already used by /v1/audio/transcriptions and causing an out-of-memory worker crash. Inline data URLs reach this path without being bounded by VLLM_AUDIO_FETCH_TIMEOUT. The issue affects deployments serving an audio-capable model, and authentication changes only the deployment-specific reachability. This issue is fixed in version 0.24.0.

Yayınlanma 16.09.2026
ISO Tarih 2026-09-16
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
0.7%
30 günlük olasılık
Tüm CVElerin 55. yüzdeliğinde — Bu açığın istismar edilme ihtimali çoğu CVEden yüksek.
AI Güvenlik Analizi

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CVE-2026-57173
CVSS 6.5/10 · ORTA · 16.09.2026
CWE: CWE-770
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 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM all…
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-770
Etkilenen Ürünler (1)
vllm:vllm (tüm sürümler)
Referanslar (4)
github.com patch
github.com patch
github.com advisory
İlgili CVE'ler
9.8
CVE-2026-112779
Grav API plugin (grav-plugin-api) 1.0.40 before 1.0.42 caches a full translation dictionary for every well-for
9.8
CVE-2026-82439
Description The DRPC server kept a map from function name to request queue and created an entry the first tim
9.8
CVE-2026-47891
A Spring WebFlux application that relies on the Aalto XML processor to parse XML input does not correctly enfo
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