CVE-2026-27940
7.8
HIGH
CVSS 3.1
EPSS 0.02%
Description
llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.
How to fix CVE-2026-27940
To remediate CVE-2026-27940, upgrade the affected package to a fixed version below.
- —upgrade to 8461+dfsg-1 or later
Is CVE-2026-27940 being exploited?
Low — EPSS is 0.0%, meaning exploitation activity has not been observed at scale.
Affected packages (1)
- from 0, < 8461+dfsg-1
CVSS scores
| Source | Version | Severity | Vector |
|---|---|---|---|
| osv | CVSS 3.1 | HIGH7.8 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |