CVE-2025-71439
MEDIUM
MEDIUM
Priority: 0.01
BB Relevance:
39/100
Published: 2026-10-27
Modified: 2026-10-28
First seen: 2026-10-29
Status: active
Attack Surface
Low Complexity
No Auth
CVSS Vector Breakdown
AV:
Local
AC:
Low
PR:
None
UI:
Passive
S:
X
AT:
None
VC:
None
VI:
None
VA:
High
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.