CVE-2026-126975

llama.cpp GGUF File Parsing Heap-based Buffer Overflow Remote Code Execution Vulnerability

Published Nov 17, 2026 CVSS 3.0 · 7.8 High EPSS n/a KEV · Not listed
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.

Analysis

AI-generated

Technical impact

A heap-based buffer overflow exists in the GGUF file parser of llama.cpp, allowing an attacker to execute arbitrary code in the context of the current process. The fault arises from insufficient validation of the length of user‑supplied data before copying it to a heap buffer. Exploitation requires user interaction, such as opening a malicious file or visiting a malicious web page that triggers the parser.

Affected Systems

All installations of llama.cpp that support parsing of GGUF files are affected. Specific version ranges are not provided by the vendor, so any release that includes the GGUF parser is potentially vulnerable until a patch is applied.

Risk and Exploitability

The CVSS score of 7.8 indicates a high impact vulnerability, while the EPSS score is unavailable, suggesting that public exploitation data is limited but the potential remains serious. The vulnerability is not listed in the CISA KEV catalog. Exploitation would likely occur when an attacker delivers a crafted GGUF file to a user, who must interact with the file or a web page that triggers its parsing. Given the remote code execution capability and the lack of public exploitation evidence, organizations should treat this as a high‑risk flaw until mitigated.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade llama.cpp to the latest release that includes the GGUF parser patch.
  • If an upgrade is not possible, prevent untrusted users from opening or submitting GGUF files and disable GGUF support in any web‑exposed contexts.
  • Monitor system logs and process activity for abnormal execution patterns associated with GGUF handling to detect attempted exploitation.

Generated by OpenCVE AI on November 18, 2026 at 09:22 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
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.
Title llama.cpp GGUF File Parsing Heap-based Buffer Overflow Remote Code Execution Vulnerability
Weaknesses CWE-122
References
Metrics cvssV3_0

{'score': 7.8, 'vector': 'CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H'}

Subscriptions

No data.

Weaknesses
  • CWE-122

    Heap-based Buffer Overflow

Sources

Status
PUBLISHED
Assigner
zdi
Published
Updated
Nov 17, 2026, 11:15 PM
Reserved
Nov 12, 2026, 3:09 AM
Status
Awaiting Analysis
Published
Nov 18, 2026, 12:18 AM
Modified
Nov 18, 2026, 12:18 AM