CVE-2025-53630
Fixed in a distro release EPSS <1%CVSS 8.9
llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the gguf_init_from_file_impl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579.
Products: ggml-org llama.cpp
Distro releases
| Release | Package | Fixed in |
|---|---|---|
| Debian 14 | ggml | 0.0~git20250711.b6d2ebd-1 |
| Debian 14 | llama.cpp | 5882+dfsg-1 |
| Ubuntu 25.10 | llama.cpp | no fix |
| Ubuntu 26.04 LTS | llama.cpp | no fix |
| Ubuntu 26.10 | llama.cpp | no fix |
| openSUSE Tumbleweed | llamacpp | 5889-1.1 |