CVE-2026-116816

HIGH8.5

llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer

Published Oct 27, 2026

Modified Yesterday

Details

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.

References

WEB

https://github.com/ggml-org/llama.cpp/blob/b10259/src/llama-vocab.cpp#L1376-L1377

FIX

https://github.com/ggml-org/llama.cpp/commit/cf06ad7dfe79e7bf2934150d4fefe1ce8db05490

FIX

https://github.com/ggml-org/llama.cpp/pull/25969

FIX

https://github.com/ggml-org/llama.cpp/pull/26511

WEB

https://github.com/ggml-org/llama.cpp/releases/tag/b10261

ADVISORY