CVE-2025-53630
Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Exploit likelihood
What each source reports
CVE List Score used
Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
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.
- Record
CVE-2025-53630- CVSS 4.0
- 8.9 High
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
- Updated
- 2026-11-02
EUVDEUVD-2025-21070
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.
- Record
EUVD-2025-21070- CVSS 4.0
- 8.9 High
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 - Updated
- 2026-11-02
NVD
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.
- Record
CVE-2025-53630- CVSS 4.0
- 8.9 High
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/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - Weakness
- CWE-122, CWE-680
- Updated
- 2026-11-02
OSV
Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
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.
- Record
CVE-2025-53630- CVSS 4.0
- 8.9 High
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
- Updated
- 2026-11-02
OSVDEBIAN-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.
- Record
DEBIAN-CVE-2025-53630- CVSS 4.0
- 8.9 High
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/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - Updated
- 2026-11-02
OSVUBUNTU-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.
- Record
UBUNTU-CVE-2025-53630- CVSS 4.0
- 8.9 High
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 - Updated
- 2026-11-02
OSVopenSUSE-SU-2025:15343-1 No score
ggml-devel-5889-1.1 on GA media
These are all security issues fixed in the ggml-devel-5889-1.1 package on the GA media of openSUSE Tumbleweed.
- Record
openSUSE-SU-2025:15343-1- Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
ggmlDebian:14 |
before 0.0~git20250711.b6d2ebd-1, plus listed versions 0.0~git20250414.be935ac-40.0~git20250414.be935ac-50.0~git20250502.17733de-10.0~git20250502.17733de-20.0~git20250502.17733de-30.0~git20250502.17733de-40.0~git20250618.9e4bee1-10.0~git20250618.9e4bee1-2 |
0.0~git20250711.b6d2ebd-1 |
llama.cppDebian:14 |
before 5882+dfsg-1, plus listed versions 5151+dfsg-1~exp25151+dfsg-1~exp35318+dfsg-15318+dfsg-25713+dfsg-1 Show 4 moreShow less5760+dfsg-15760+dfsg-25760+dfsg-35760+dfsg-4 |
5882+dfsg-1 |
llama.cppUbuntu:25.10 |
All versions, plus listed versions 5318+dfsg-15318+dfsg-25713+dfsg-15760+dfsg-15760+dfsg-35760+dfsg-45882+dfsg-2 |
None known |
llama.cppUbuntu:26.10 |
All versions, plus listed versions 8681+dfsg-19721+dfsg-1ubuntu110438+dfsg-110438+dfsg-1ubuntu1 |
None known |
llama.cppUbuntu:26.04:LTS |
All versions, plus listed versions 5882+dfsg-28064+dfsg-1ubuntu18681+dfsg-1 |
None known |
llamacppopenSUSE:Tumbleweed |
before 5889-1.1 | 5889-1.1 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2025-53630 is a high vulnerability (CVSS 8.9) in Ggml-org Llama.cpp, published July 10, 2025. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.36%, the 30th percentile. Fixed in ggml 0.0~git20250711.b6d2ebd-1.
References
github.com/ggml-org/llama.cpp/security/advisories/GHSA-vgg9-87g3-85w8
nvd.nist.gov/vuln/detail/CVE-2025-53630
security-tracker.debian.org/tracker/CVE-2025-53630
ubuntu.com/security/CVE-2025-53630
cve.org/CVERecord?id=CVE-2025-53630
suse.com/security/cve/CVE-2025-53630