EUVD-2025-18632
CVSS Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Lifecycle Timeline
4Tags
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.
Analysis
A buffer overflow vulnerability in llama.cpp (CVSS 8.8). High severity vulnerability requiring prompt remediation. Vendor patch is available.
Technical Context
CWE-119 (Buffer Overflow). CVSS 8.8 indicates high severity. Affects llama.cpp.
Affected Products
['llama.cpp']
Remediation
Apply the vendor-supplied patch immediately. Consider network segmentation to limit exposure if patching is delayed.
Priority Score
Vendor Status
Ubuntu
Priority: Medium| Release | Status | Version |
|---|---|---|
| jammy | DNE | - |
| noble | DNE | - |
| oracular | DNE | - |
| plucky | DNE | - |
| upstream | needs-triage | - |
| questing | needs-triage | - |
Debian
Bug #1108113| Release | Status | Fixed Version | Urgency |
|---|---|---|---|
| sid | fixed | 8064+dfsg-2 | - |
| (unstable) | fixed | 5713+dfsg-1 | - |
Share
External POC / Exploit Code
Leaving vuln.today