CVE-2025-53630
llama.cpp is an inference of several LLM models in C/C++. Integer Over ...
Overview
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.
Source: OX vulnerability database
Severity
8.9 · HIGH
CVSS 4.0 base score, scored by NVD.
- Attack vector
- Network
- Attack complexity
- Low
- Attack requirements
- None
- Privileges required
- None
- User interaction
- None
- Vulnerable system confidentiality
- High
- Vulnerable system integrity
- High
- Vulnerable system availability
- High
- Subsequent system confidentiality
- None
- Subsequent system integrity
- None
- Subsequent system availability
- None
- E
- P
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:P
Weakness: CWE-122, CWE-680
Affected packages · 0
No registry package. This ID affects operating system packages only.
Operating systems · 3 fixes
debian 1 release · 2 packages
| Release | Package | Fixed in |
|---|---|---|
| 14 | ggml | 0.0~git20250711.b6d2ebd-1 |
| 14 | llama-cpp | 5882+dfsg-1 |
openSUSE 1 release · 1 package
| Release | Package | Fixed in | Advisory |
|---|---|---|---|
| Tumbleweed | ggml-devel +9 | 5889-1.1 | openSUSE-SU-2025:15343-1 |
References
OX Radar and Response Center
Find threats in your stack.
OX Radar can check high-priority threats, like critical package CVEs, against your context.
Each incident is marked Detected or Not Detected with a remediation plan and proof all tracked in the Response Center.