Debian/llama.cpp: unknown
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 i
Action: Upgrade llama.cpp to 5882+dfsg-1 or later.
Affected
| introduced | fixed | last affected |
|---|---|---|
| 0 | 5882+dfsg-1 | - |
Fixed versions
| 5882+dfsg-1 |
Sources
- osv: DEBIAN-CVE-2025-53630#Debian:14/llama.cpp
- https://security-tracker.debian.org/tracker/CVE-2025-53630
published · modified · JSON