CVE-2025-49847

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.

The following products are affected by CVE-2025-49847 vulnerability.

Here, you will find a curated list of external links that provide in-depth information to CVE-2025-49847.

URL	Resource
https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr