CVE-2025-53630
highpriority · track · 0EPSS 0.004 · 30 %ileDEEUEPSS · scored 2026-10-27
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
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (4)
Products and version ranges known to be affected.
advisories (1)
Vendor and ecosystem advisories describing this.
- WID-SEC-W-2025-1747HCL DominoIQ (llama.cpp): Mehrere Schwachstellen ermöglichen CodeausführungDeutsch2025-08-07csaf · cert_bundDE
Ein entfernter, anonymer Angreifer kann mehrere Schwachstellen in HCL Domino ausnutzen, um beliebigen Programmcode auszuführen.
also known as (2)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (9)
External citations — patches, advisories, analysis.
- https://access.redhat.com/security/cve/cve-2025-53630cnnvd
- https://github.com/ggml-org/llama.cpp/commit/26a48ad699d50b6268900062661bd22f3e792579cnnvd
- https://github.com/ggml-org/llama.cpp/releasesPatchcnnvd
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-vgg9-87g3-85w8cnnvd
- https://nvd.nist.gov/vuln/detail/CVE-2025-53630cnnvd
- https://github.com/ggml-org/llama.cpp/commit/26a48ad699d50b6268900062661bd22f3e792579enisa_euvd
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-vgg9-87g3-85w8enisa_euvd
- https://github.com/ggml-org/llama.cpp/commit/26a48ad699d50b6268900062661bd22f3e792579nvd
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan