llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
概要
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
原文の説明
取得元が公開している説明をそのまま載せています (多くは英語)。
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.
出典: OSV.dev (Open Source Vulnerabilities) NVD GitHub Advisory OSV
ディストリビューション別の修正状況
各ディストリビューションが公開している、この CVE の修正パッケージ
- Debian DEBIAN-CVE-2025-49847 llama.cpp 修正版: 5713+dfsg-1
- Ubuntu UBUNTU-CVE-2025-49847 llama.cpp
参照URL
- advisory github.com
- advisory github.com
- advisory nvd.nist.gov
- patch github.com