CVE-2026-27940

HIGH EPSS 7.4%
Published Mar 12, 20263mo ago · Modified Jun 17, 20262w ago
7.8 CVSS 3.1
High
Find Similar
Published Mar 12, 2026 3mo ago
Last Modified Jun 17, 2026 2w ago

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.

CVSS Details

Base Score
7.8
Exploitability
1.8
Impact
5.9
Vector string
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack Vector Local
Attack Complexity Low
Privileges Required None
User Interaction Required
Scope Unchanged
Confidentiality High
Integrity High
Availability High

Threat Intelligence

EPSS Exploit Probability
7.4% percentile
Exploit & Patch Status
Public Exploit Known
No Patch Available

Weaknesses 2

CWE-122
CWE-190 Integer Overflow or Wraparound Numeric Error

Affected Products 1

VendorProductVersionRange
ggmlllama.cpp* <b8146

References 1

  • github.com https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v
    ExploitVendor Advisory

Remediation

No remediation data recorded yet

Check vendor advisories and the NVD entry for patch availability.