PT-2026-125542

CVE-2025-71439

Published

2026-10-27

Updated

2026-10-27

Description by

CVSS 4.0

6.8

Medium

MetricsAV:L/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Name of the Vulnerable Software and Affected Versions llama.cpp versions prior to b5649

Description A heap out-of-bounds read occurs in the llama vocab::impl::print info() function. This issue allows an attacker to crash the model loading process by providing a specially crafted GGUF model containing oversized special token IDs and a short tokenizer.ggml.tokens array. This causes llama-cli or llama-server to read past the id to token boundary, resulting in a crash.

Recommendations Update llama.cpp to version b5649 or later.

Exploitability

Exploit

Fix

Impacts

Researchers

Ggerganov

Jeongwoo Lee

Miaoqian Lin

Vendors

Affected products

Weakness enumeration