CVE-2024-21836Published Feb 26, 2024 · Feb 26Updated Jun 17
A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp Com…
llama.cpp
High8.8
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| llama.cpp llama.cpp |
| No fix yet |
Original 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.
From the CVE record · talos