CVE-2025-71439

Description

llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash.

References

• https://github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp#L2771
• https://github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752c9cac
• https://github.com/ggml-org/llama.cpp/pull/14145
• https://github.com/ggml-org/llama.cpp/releases/tag/b5649
• https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6