CVE-2026-126975
7.8HighPublished 18 Nov 2026 · NVD status: Awaiting Analysis · AI triage by gemini-3.1-flash-lite
High
0CVSS v3.010
- Attack vector
- Local
- Complexity
- Low
- Privileges
- None
- User action
- Required
- Impact
- Full C/I/A compromise
- Weakness
- CWE-122
What an attacker gets
Remote attackers can execute arbitrary code on your system by providing a malicious GGUF file. A user must open the file or visit a page that triggers the parser for this to occur.
Root cause
The GGUF file parser fails to validate the length of user-supplied data before copying it into a heap-based buffer.
Affected versions
Versions not listed — check the vendor advisory.
CVSS v3.0 · CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Fix & remediation
Update to the latest version of llama.cpp from the official repository. Avoid opening untrusted GGUF files until the patch is applied.
$ git pull && make clean && makeAI-suggested. Run it in staging first and check it against the vendor advisory. Why?
NVD description
llama.cpp GGUF File Parsing Heap-based Buffer Overflow Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of llama.cpp. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The specific flaw exists within the parsing of GGUF files. The issue results from the lack of proper validation of the length of user-supplied data prior to copying it to a heap-based buffer. An attacker can leverage this vulnerability to execute arbitrary code in the context of the current process. Was ZDI-CAN-34558.