csirt@kutim:~/threat-intel/cve/CVE-2025-48887

Katalog CVE

CVSS 6.5 · Medium EPSS 0,52%

Kerentanan Inefficient Regular Expression Complexity pada vllm. Skor CVSS 3.1 6.5 (Medium) menurut github.com.

Deskripsi (NVD)

vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an attacker to cause severe performance degradation or make the service unavailable. The pattern contains multiple nested quantifiers, optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking. Version 0.9.0 contains a patch for the issue.

Rincian

Terbit di NVD
30 Mei 2025
Terakhir diubah
17 Juni 2026
Status NVD
Analyzed
CVSS 3.1
6.5 (Medium), sumber github.com
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H · uraikan di kalkulator
Jenis kelemahan (CWE)
CWE-1333: Inefficient Regular Expression Complexity
EPSS (30 hari)
0,52% peluang dieksploitasi; lebih tinggi dari 42,4% CVE lain

Produk dan versi terdampak

VendorProdukVersi terdampak
vllm vllm Versi 0.6.4 hingga sebelum 0.9.0

> Data dari konfigurasi CPE di NVD.

Referensi dan perbaikan

Sumber: NVD · CVE.org · EPSS. Halaman ini disusun otomatis dari data tersebut; pembaruan terakhir 5 Okt 2026, 20:11 WITA. Kalau sistem di Perangkat Daerah memakai produk ini dan butuh bantuan, laporkan lewat kanal pelaporan.