CVE-2025-49847
Publication date 17 June 2025
Last updated 25 June 2025
Ubuntu priority
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.
Status
| Package | Ubuntu Release | Status |
|---|---|---|
| llama.cpp | 26.04 LTS resolute |
Needs evaluation
|
| 25.10 questing |
Needs evaluation
|
|
| 24.04 LTS noble | Not in release | |
| 22.04 LTS jammy | Not in release |
Severity score breakdown
| Parameter | Value |
|---|---|
| Base score |
8.8 · High
|
| Attack vector | Network |
| Attack complexity | Low |
| Privileges required | None |
| User interaction | Required |
| Scope | Unchanged |
| Confidentiality | High |
| Integrity impact | High |
| Availability impact | High |
| Vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
References
Other references
- https://www.cve.org/CVERecord?id=CVE-2025-49847
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr
- https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5 (b5662)
- https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5