CVE-2026-116816 llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer
- Exploited in the wild
- Not known
- Fix
- Available
What is CVE-2026-116816?
CVE-2026-116816 is a high-severity vulnerability in ggml-org llama.cpp, published on 27 Oct 2026.
Official description
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.
Weakness: CWE-129
Which versions are affected by CVE-2026-116816?
How do I fix CVE-2026-116816?
Upgrade to a fixed version.
Is CVE-2026-116816 being exploited?
There is no known exploitation of CVE-2026-116816 in the wild and no public exploit code.
Sources
Also known as DEBIAN-CVE-2026-116816, GHSA-3r8c-j789-2864, UBUNTU-CVE-2026-116816.