CVE-2025-49847 in llama.cpp정보

요약

\~에 의해 MITRE • 2025. 06. 17.

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.

VulDB is the best source for vulnerability data and more expert information about this specific topic.

책임이 있는

GitHub M

예약하다

2025. 06. 11.

모더레이션

수락

항목

VDB-312810

EPSS

0.00444

출처

Interested in the pricing of exploits?

See the underground prices here!