CVE-2025-53630
Unknown Unknown - Not Provided
BaseFortify

Publication date: 2025-07-10

Last updated on: 2025-07-15

Assigner: GitHub, Inc.

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.
CVSS Scores
EPSS Scores
Probability:
Percentile:
Meta Information
Published
2025-07-10
Last Modified
2025-07-15
Generated
2026-05-07
AI Q&A
2025-07-10
EPSS Evaluated
2026-05-05
NVD
EUVD
Affected Vendors & Products
Showing 1 associated CPE
Vendor Product Version / Range
ggml llama.cpp *
Helpful Resources
Exploitability
CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
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().
CWE-680 The product performs a calculation to determine how much memory to allocate, but an integer overflow can occur that causes less memory to be allocated than expected, leading to a buffer overflow.
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?

This vulnerability is an Integer Overflow in the gguf_init_from_file_impl function within the ggml/src/gguf.cpp file of llama.cpp, which is a C/C++ implementation for inference of several large language models (LLMs). The integer overflow can cause a Heap Out-of-Bounds Read or Write, potentially leading to memory corruption or crashes. This issue has been fixed in a specific commit.


How can this vulnerability impact me? :

The vulnerability can lead to Heap Out-of-Bounds Read or Write, which may cause application crashes, memory corruption, or potentially allow an attacker to execute arbitrary code or cause denial of service when processing malicious input files.


What immediate steps should I take to mitigate this vulnerability?

Update llama.cpp to include the fix from commit 26a48ad699d50b6268900062661bd22f3e792579, which addresses the integer overflow in ggml/src/gguf.cpp. Until the update is applied, avoid processing untrusted input with the vulnerable function to reduce risk.


Ask Our AI Assistant
Need more information? Ask your question to get an AI reply (Powered by our expertise)
0/70
EPSS Chart