vLLM: Forged multimodal UUID + P0/P1 processor-cache eviction drift: unauthenticated remote crash of the whole vLLM engine
影響: pip:vllm < 0.31.0 → 0.31.0
Multimodal content parts (image_url, video_url, input_audio, ...) accept a user-supplied uuid field that vLLM uses verbatim as the item's cache identity (mm_hash). The two frontend/engine processor caches (P0 "sender" cache in the API process, P1 "receiver" cache in the EngineCore process) are independent LRU caches whose evictions are not synchronized, and the P1 hit path performs zero consistency validation — it silently substitutes the cached item's tensor data for whatever the current reque…
| CVE | CVE-2026-114050 |
|---|---|
| 정보원 | GitHub Advisory Database |
| 수집 시각 | 2026. 10. 24. 오후 01:50 |
| 데이터 | Markdown JSON |
2026. 10. 24. 오전 05:43, GitHub Advisory Database에서 "vLLM: Forged multimodal UUID + P0/P1 processor-cache eviction drift: unauthenticated remote crash of the whole vLLM engine"을(를) 게시했습니다 (유형: 취약점 권고). 심각도는 "보통"(medium)입니다. 관련 기술: Python. CVE: CVE-2026-114050.