
We found results for “”
CVE-2025-49847
Good to know:

Date: June 17, 2025
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.
Severity Score
Related Resources (5)
Severity Score
Weakness Type (CWE)
Top Fix

CVSS v3.1
Base Score: |
|
---|---|
Attack Vector (AV): | NETWORK |
Attack Complexity (AC): | LOW |
Privileges Required (PR): | NONE |
User Interaction (UI): | REQUIRED |
Scope (S): | UNCHANGED |
Confidentiality (C): | HIGH |
Integrity (I): | HIGH |
Availability (A): | HIGH |