icon

We found results for “

CVE-2025-49847

Good to know:

icon

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

Severity Score

Weakness Type (CWE)

Improper Restriction of Operations within the Bounds of a Memory Buffer

CWE-119

Signed to Unsigned Conversion Error

CWE-195

Top Fix

icon

Upgrade Version

Upgrade to version https://github.com/ggml-org/llama.cpp.git - b5662

Learn More

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

Do you need more information?

Contact Us