Buffer overflow in Ggml Llama.cpp

CVE-2026-27940

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.

Vulnerability class: Buffer Overflow

Published · last modified .

CVSS v3 metric

CVSS v3 base score 7.8 (High). Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.

EPSS exploit prediction

EPSS: 0.002 (6.9th percentile), scored .

Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 7th percentile — 6.9% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.

EPSS trend (30 days)EPSS over the last 30 days for CVE-2026-27940: held from 0.002 to 0.002.

EPSS over last 30 days · oldest: 0.002 · newest: 0.002 · change: +0.000

Affected products

Weakness classification (CWE)

Public proof-of-concept exploits

References

Frequently asked questions

What is CVE-2026-27940?
CVE-2026-27940 is a high-severity vulnerability in Ggml Llama.cpp, classified under Heap-based Buffer Overflow. CVSS score: 7.8/10. Published 2026-03-12.
How severe is CVE-2026-27940?
High severity. CVSS v3 base score is 7.8 out of 10.
Is CVE-2026-27940 known to be exploited?
1 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.