CVE-2025-46722

Katalog CVE

CVSS 7.3 · High EPSS 0,32%

Kerentanan Incomplete Comparison with Missing Factors pada vllm. Skor CVSS 3.1 7.3 (High) menurut NVD.

Deskripsi (NVD)

vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks. This issue has been patched in version 0.9.0.

Rincian

Terbit di NVD

29 Mei 2025

Terakhir diubah

17 Juni 2026

Status NVD

Analyzed

CVSS 3.1

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

Jenis kelemahan (CWE)

CWE-1023: Incomplete Comparison with Missing Factors
CWE-1288: Improper Validation of Consistency within Input

EPSS (30 hari)

0,32% peluang dieksploitasi; lebih tinggi dari 23,6% CVE lain

Produk dan versi terdampak

> Data dari konfigurasi CPE di NVD.

Referensi dan perbaikan

• https://github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6 advisory vendor
• https://github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848 patch
• https://github.com/vllm-project/vllm/pull/17378 issue tracking · patch