cvedb.io
CVE-2025-49847
HIGH · CVSS 8.8
EPSS exploitation probability: 0%
Published 2025-06-17T20:15:32.437 · Last modified 2026-06-17T09:32:00.730

Summary

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.

Affected products

ggml — llama.cpp

Does this affect you?

Add your gear to cvedb and we'll alert you only when ggml ships something exploited.

Check my exposure →

References

This product uses data from the NVD API but is not endorsed or certified by the NVD. Informational only; not professional security advice.