CVE-2025-71439EPSS p1.9%

CVE-2025-71439CVE-2025-71439

Description

llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash.

Scoring

CVSS 5.5 ()
VectorCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
EPSS0.12% probability of exploitation · percentile 1.9% · 2026-10-27T12:03:15Z
Last modified2026-10-27
Sourced from NVD + FIRST.org EPSS. Curated for EU compliance use cases by Adam Lundqvist, Founder at SQUR.