Live › vulnerability › CVE-2026-116816
Go to dashboardllama.cpp's PLaMo-2 tokenizer accepts a byte token such as <0x-1> whose negative value writes token ids before its heap buffer while a model loads. A crafted GGUF model file can corrupt heap memory, causing crashes or possibly code execution.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-27 01:34 UTC. All times on this page are UTC.
Teams that run llama.cpp builds from b5899 up to but not including and load GGUF model files, especially ones from outside sources or user uploads. Teams on newer builds or that only load models they built or verified themselves can skip it.
b10261No product ranges from the sources yet.
llama-cli --version or check the build tag and compare it against b10261; builds from b5899 up to but not including b10261 are affected.b10261 or later.Each row is the first time that source carried this signal. The analyst’s rows are its own findings.
llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm_tokenizer_plamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like <0x-1> whose negative parsed value writes token ids before the bytes_ buffer during model loading, causing crashes or potential code execution.
This page as .md · .json · in your agent: get_signal("CVE-2026-116816")
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.