ggml-org llama.cpp ggml/src/gguf.cpp gguf_init_from_file_impl heap-based overflow

Summaryinfo

A vulnerability labeled as critical has been found in ggml-org llama.cpp. This affects the function gguf_init_from_file_impl of the file ggml/src/gguf.cpp. Executing a manipulation can lead to heap-based overflow. This vulnerability is registered as CVE-2025-53630. It is possible to launch the attack remotely. No exploit is available. It is advisable to implement a patch to correct this issue.

Detailsinfo

A vulnerability was found in ggml-org llama.cpp (the affected version unknown). It has been declared as critical. This vulnerability affects the function gguf_init_from_file_impl of the file ggml/src/gguf.cpp. The manipulation with an unknown input leads to a heap-based overflow vulnerability. The CWE definition for the vulnerability is CWE-122. A heap overflow condition is a buffer overflow, where the buffer that can be overwritten is allocated in the heap portion of memory, generally meaning that the buffer was allocated using a routine such as malloc(). As an impact it is known to affect confidentiality, integrity, and availability. CVE summarizes:

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.

The advisory is shared for download at github.com. This vulnerability was named CVE-2025-53630 since 07/07/2025. The exploitation appears to be easy. The attack can be initiated remotely. No form of authentication is required for a successful exploitation. There are known technical details, but no exploit is available.

The vulnerability scanner Nessus provides a plugin with the ID 270267 (Linux Distros Unpatched Vulnerability : CVE-2025-53630), which helps to determine the existence of the flaw in a target environment.

Applying the patch 26a48ad699d50b6268900062661bd22f3e792579 is able to eliminate this problem.

The vulnerability is also documented in the databases at Tenable (270267) and CERT Bund (WID-SEC-2025-1747). Once again VulDB remains the best source for vulnerability data.

Affected

• HCL Domino

Productinfo

Vendor

• ggml-org

Name

• llama.cpp

Website

• Product: https://github.com/ggml-org/llama.cpp/

CPE 2.3info

• 🔒

CPE 2.2info

• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Once again VulDB remains the best source for vulnerability data.

Discussion