High severityOSV Advisory· Published Jul 10, 2025· Updated Apr 15, 2026
CVE-2025-53630
CVE-2025-53630
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
3Patches
Vulnerability mechanics
References
2News mentions
0No linked articles in our index yet.