CWE-400
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.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
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]