CVE-2025-49847
8.8
Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Exploitability: 2.8 / Impact: 5.9
Source: security-advisories@github.com (Secondary)
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.
Affected (1)
Related CWEs
CWE-119
Improper Restriction of Operations within the Bounds of a Memory Buffer
The product performs operations on a memory buffer, but it reads from or writes to a memory location outside the buffer's intended boundary. This may result in read or write operations on unexpected memory locations that could be linked to other variables, data structures, or internal program data.
CWE-195
Signed to Unsigned Conversion Error
The product uses a signed primitive and performs a cast to an unsigned primitive, which can produce an unexpected value if the value of the signed primitive can not be represented using an unsigned primitive.
References (2)
Source: security-advisories@github.com
Patch
Source: security-advisories@github.com
MitigationVendor Advisory
Timeline
No history available yet.