CVE-2025-49847
Description
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.
How to fix CVE-2025-49847
To remediate CVE-2025-49847, upgrade the affected package to a fixed version below.
- —upgrade to 5713+dfsg-1 or later
Is CVE-2025-49847 being exploited?
Low — EPSS is 0.6%, meaning exploitation activity has not been observed at scale.
Affected packages (1)
- from 0, < 5713+dfsg-1
CVSS scores
| Source | Version | Severity | Vector |
|---|---|---|---|
| osv | CVSS 3.1 | HIGH8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |