Skip to content

CVE-2024-21836 A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp Commit 18c2e17. A specially crafted .gguf file can lead to code execution. An attacker...

CriticalCVSS 9.8 EPSS 1.3%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
No known exploitation · automatable: no · technical impact: total
Technology
Debian

Description

A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp Commit 18c2e17. A specially crafted .gguf file can lead to code execution. An attacker can provide a malicious file to trigger this vulnerability.

Upgrade path

3 packages: 1 fixed.

PackageAffectedFixed inStatus
ggml llama.cpp < 2024-01-09 2024-01-09 Fixed
ggerganov llama.cpp = 18c2e17 No fix listed Versions listed
llama.cpp = Commit 18c2e17 No fix listed Versions listed

Affected products

ProductAffected versionsFixed in
llama.cpp = Commit 18c2e17 No fix listed
ggerganov llama.cpp = 18c2e17 No fix listed
ggml llama.cpp < 2024-01-09 2024-01-09

References