CVSS 6.5 · Medium EPSS 0,27%
Kerentanan Improper Input Validation pada vllm. Skor CVSS 3.1 6.5 (Medium) menurut github.com.
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
· uraikan di kalkulator | Vendor | Produk | Versi terdampak |
|---|---|---|
| vllm | vllm | Semua versi sebelum 0.30.0 |