Integer overflow in llama.cpp - CVE-2025-53630

Detailed vulnerability description

The vulnerability allows a remote attacker to execute arbitrary code on the target system.

The vulnerability exists due to integer overflow in the "gguf_init_from_file_impl" function within ggml/src/gguf.cpp. A remote attacker can pass specially crafted data to the application, trigger integer overflow and execute arbitrary code on the target system.

Successful exploitation of this vulnerability may result in complete compromise of vulnerable system.

How to mitigate CVE-2025-53630

Sources

• https://github.com/ggml-org/llama.cpp/commit/26a48ad699d50b6268900062661bd22f3e792579
• https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-vgg9-87g3-85w8