CVE-2026-73559

Açıklama ve Etki

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_completion() in vllm/renderers/online_renderer.py expand every element, and vllm/entrypoints/openai/completion/serving.py creates one engine generator and response slot per prompt, allowing an authenticated API client to exhaust CPU, memory, async scheduling capacity, engine request slots, and response buffering with one request. This issue is fixed in version 0.26.0.

Referanslar

• https://github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e
• https://github.com/vllm-project/vllm/pull/47845
• https://github.com/vllm-project/vllm/releases/tag/v0.26.0
• https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j

Güvenli Doğrulama Notu

Bu sayfa saldırı gerçekleştiren payload'lar çalıştırmaz. Doğrulama; etkilenen ürün/sürümün envanterden kontrol edilmesi, üretici güvenlik duyurusunun incelenmesi ve güncellemenin uygulanması üzerinden yapılmalıdır.