CVE-2026-116816 llama.cpp - Out of Bounds Read/Write

llama.cpp before b10261 contains a heap out-of-bounds write caused by improper handling of BYTE-typed token text in llm_tokenizer_plamo2::build, letting attackers corrupt heap memory via crafted GGUF models, exploit requires crafted model input.

CVSS base score 7.8 /10
High
CISA KEV
Not listed
Public exploit
None known
Authentication
Not required
View the NVD record ↗