CVE-2025-53630

HIGHCVSS 8.9/10EPSS 0.32%

Last modified

CVE-2025-53630 is a high-severity vulnerability rated 8.9/10 on the CVSS scale. 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. EPSS estimates a 0.32% chance of exploitation in the next 30 days.

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.

Metrics

Weakness Enumeration

References

Timeline

Published
Last Modified
Status
Deferred

Frequently Asked Questions

What is CVE-2025-53630?
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.
How severe is CVE-2025-53630?
CVE-2025-53630 has a CVSS score of 8.9/10 (HIGH severity). The EPSS model estimates a 0.32% probability of exploitation in the next 30 days.
How do I fix CVE-2025-53630?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2025

Are you affected by CVE-2025-53630?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST