Description
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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| ggml-org | llama.cpp | < 26a48ad699d50b6268900062661bd22f3e792579 | — |
Fixed in Linux distributions
Distributions backport fixes, so the version that fixes this vulnerability differs per release — upgrade to at least the version shown. From the distributions' security trackers and advisories.
Debian
Security tracker ↗| Release | Package | Fixed in | Advisory |
|---|---|---|---|
| Debian 14 | ggml | 0.0~git20250711.b6d2ebd-1 | — |
| Debian 14 | llama.cpp | 5882+dfsg-1 | — |
Ubuntu
Security tracker ↗| Release | Package | Fixed in | Advisory |
|---|---|---|---|
| Ubuntu 26.10 | llama.cpp | No fix yet | — |
| Ubuntu 26.04 LTS | llama.cpp | No fix yet | — |
| Ubuntu 25.10 | llama.cpp | No fix yet | — |
openSUSE
Security tracker ↗| Release | Package | Fixed in | Advisory |
|---|---|---|---|
| openSUSE Tumbleweed | llamacpp | 5889-1.1 | openSUSE-SU-2025:15343-1 |
Advisories 2
- openSUSE-SU-2025:15343-1 ggml-devel-5889-1.1 on GA media SUSE / openSUSE Security Updates · Mar 23, 2026
- WID-SEC-2025-1747 HCL DominoIQ (llama.cpp): Mehrere Schwachstellen ermöglichen Codeausführung BSI CERT-Bund (WID) · Aug 7, 2025