CVE-2025-49847
CVE.org · Published
- Record status
- Published
- Identifier year (not publication year)
- 2025
- Source publication
- Source updated
- Imported by cveboard
- Source snapshot
- cve_2026-10-24_midnight_baseline ·
CNA source text (English)
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
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.
Scoped product and version facts
Fix information unknown; no fixed version is derived here. Missing information does not prove that no fix exists.
Exploitation unknown; this catalogue does not assess exploitation.
llama.cpp
- Vendor
- ggml-org
- Product
- llama.cpp
- Platforms
- Unknown
- Default status
Unknown
| Version (version) | Status (status) | Version scheme (versionType) | Exclusive end (lessThan) | Inclusive end (lessThanOrEqual) | Status changes (at → status) |
|---|---|---|---|---|---|
| < b5662 | affected | Unavailable | Unavailable | Unavailable | None listed |