Skip to main content

Over 150 LLM Providers · Over 5,300 Models The most extensible AI-powered pentesting platform. Open source. Star on GitHub

CVE-2024-32878

7.1 · HIGH
Published Apr 26, 2024 ggml CWE-456 EPSS 0.70% (50th pctl)

Overview

CVE-2024-32878 is a high-severity vulnerability affecting ggml llama.cpp. It was published on April 26, 2024 and has a CVSS 3.1 base score of 7.1 (HIGH).

This vulnerability has a CVSS 3.1 base score of 7.1, rated HIGH. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.

Technical Description

Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in gguf_init_from_file, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this uninitialized value and cause arbitrary address free problems. This may further lead to be exploited. Causes llama.cpp to crash (DoS) and may even lead to arbitrary code execution (RCE). This vulnerability has been patched in commit b2740.

Remediation

Check the references section for vendor advisories and patches from ggml. Update llama.cpp to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

Affected Products

Vendor Product Versions Status
ggml llama.cpp >= b2715, < b2740 Affected

Frequently Asked Questions

What is CVE-2024-32878?

CVE-2024-32878 is a high-severity vulnerability affecting ggml llama.cpp. It was published on April 26, 2024 and has a CVSS 3.1 base score of 7.1 (HIGH).

How severe is CVE-2024-32878?

This vulnerability has a CVSS 3.1 base score of 7.1, rated HIGH. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.

How do I fix or remediate CVE-2024-32878?

Check the references section for vendor advisories and patches from ggml. Update llama.cpp to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

How can CyberStrike help with CVE-2024-32878?

CyberStrike's AI-powered security agents can automatically detect CVE-2024-32878 across your infrastructure using autonomous pentesting, DAST scanning, and HackBrowser. The platform continuously monitors for known vulnerabilities and provides actionable remediation guidance prioritized by real-world exploitability.