CVE-2025-24357

Katalog CVE

CVSS 8.8 · High EPSS 0,87%

Kerentanan Deserialization of Untrusted Data pada vllm. Skor CVSS 3.1 8.8 (High) menurut NVD.

Deskripsi (NVD)

vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it will execute arbitrary code during unpickling. This vulnerability is fixed in v0.7.0.

Rincian

Terbit di NVD

27 Januari 2025

Terakhir diubah

17 Juni 2026

Status NVD

Analyzed

CVSS 3.1

8.8 (High), sumber NVD
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H · uraikan di kalkulator

Jenis kelemahan (CWE)

CWE-502: Deserialization of Untrusted Data

EPSS (30 hari)

0,87% peluang dieksploitasi; lebih tinggi dari 57,6% CVE lain

Produk dan versi terdampak

> Data dari konfigurasi CPE di NVD.

Referensi dan perbaikan

• https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54 advisory vendor
• https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04 patch
• https://github.com/vllm-project/vllm/pull/12366 issue tracking · patch
• https://pytorch.org/docs/stable/generated/torch.load.html deskripsi teknis