Skip to content

CVE-2024-32878 Use of Uninitialized Variable Vulnerability in llama.cpp

HighCVSS 8.8 EPSS 0.70%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
Proof of concept public · automatable: no · technical impact: total
Technology
Debian

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.

Upgrade path

2 packages: 2 fixed.

PackageAffectedFixed inStatus
ggerganov llama.cpp <= b2715; = <= b2715 after b2715 Fixed
ggml llama.cpp >= b2715, < b2740 b2740 Fixed

Affected products

ProductAffected versionsFixed in
ggerganov llama.cpp = <= b2715 No fix listed
ggerganov llama.cpp <= b2715 No fix listed
ggml llama.cpp >= b2715, < b2740 b2740

References