Mend.io Vulnerability Database

What is a CVE vulnerability ID? icon What is a WS vulnerability ID? icon What is an MSC vulnerability ID? icon
New vulnerability? Tell us about it!
icon

We found results for “”

CVE-2025-53630

Good to know:

icon

Date: July 10, 2025

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.

Severity Score

Related Resources (5)

https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-vgg9-87g3-85w8
https://github.com/ggml-org/llama.cpp/commit/26a48ad699d50b6268900062661bd22f3e792579
https://nvd.nist.gov/vuln/detail/CVE-2025-53630
https://security-tracker.debian.org/tracker/CVE-2025-53630
https://www.mend.io/vulnerability-database/CVE-2025-53630

Severity Score

Weakness Type (CWE)

Heap-based Buffer Overflow

CWE-122

Integer Overflow to Buffer Overflow

CWE-680

Top Fix

icon

Upgrade Version

Upgrade to version https://github.com/ggml-org/llama.cpp.git - b5854

Learn More

CVSS v3.1

Base Score:
Attack Vector (AV): NETWORK
Attack Complexity (AC): LOW
Privileges Required (PR): NONE
User Interaction (UI): NONE
Scope (S): UNCHANGED
Confidentiality (C): HIGH
Integrity (I): HIGH
Availability (A): HIGH

Do you need more information?

Contact Us