Vulnerability 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.
Related Weaknesses (CWE)
References
- https://github.com/ggml-org/llama.cpp/commit/26a48ad699d50b6268900062661bd22f3e7
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-vgg9-87g3-85w8
FAQ
What is CVE-2025-53630?
CVE-2025-53630 is a documented vulnerability. 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...
How severe is CVE-2025-53630?
CVSS scoring is not yet available for CVE-2025-53630. Check NVD for updates.
Is there a patch for CVE-2025-53630?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.