Skip to content
Fencer Intel
high 8.9

CVE-2025-53630 json

Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf

published last yr. modified 4mo ago also EUVD-2025-21070

cvss
8.9
version 4.0, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 30%
public exploits
0
none known

Summary

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.

Patch / fix

  • ggerganov llama.cpp 26a48ad
  • ggml llama.cpp 26a48ad
  • ggml Debian 14 0.0~git20250711.b6d2ebd-1
  • llama.cpp Debian 14 5882+dfsg-1

debian advisories DEBIAN-CVE-2025-53630

  • llamacpp openSUSE Tumbleweed 5889-1.1

opensuse advisories openSUSE-SU-2025:15343-1

Is CVE-2025-53630 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2025-53630 updated cvss 8.1

llama.cpp: Integer Overflow in llama.cpp

  • Red Hat All currently supported Red Hat products
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
partial
Assessed
last yr.

Exploit prediction

0.36% chance of exploitation in the next 30 days, higher than 30% of all scored CVEs (FIRST EPSS, 2026-11-09).

CVSS scores

assigned by version score vector
CNA 4.0 8.9 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
CNA 4.0 8.9 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

Affected products

  • ggml-org llama.cpp

Classification

Weakness
  • CWE-122 Heap-based Buffer Overflow
  • CWE-680 Integer Overflow to Buffer Overflow

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.