Advisory

DEBIAN-CVE-2025-53630

Also known as: CVE-2025-53630

Summary

The record has no summary.

Details

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.

Severity

Not rated by the source.

Dates

Published
2025-07-10 20:15 UTC
Modified
2026-09-01 20:05 UTC

Affected packages and fixes

ggml

Debian packages (deb) · Debian 14

Affected

  • introduced 0, fixed 0.0~git20250711.b6d2ebd-1 (ecosystem)

Fixed versions

0.0~git20250711.b6d2ebd-1

Fix

  • Fixed version 0.0~git20250711.b6d2ebd-1
    sudo apt-get update && sudo apt-get upgrade

This command upgrades the distribution's packages. Compare the fixed version with the version you have installed.

llama.cpp

Debian packages (deb) · Debian 14

Affected

  • introduced 0, fixed 5882+dfsg-1 (ecosystem)

Fixed versions

5882+dfsg-1

Fix

  • Fixed version 5882+dfsg-1
    sudo apt-get update && sudo apt-get upgrade

This command upgrades the distribution's packages. Compare the fixed version with the version you have installed.

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: Debian Security Tracker (converted by OSV.dev)

Debian Security Tracker, converted to OSV by OSV.dev.

Sources & licences