Downloads · 30 days
15
7% of all-time downloads
Abhnv7/huntr-poc-bug06-llamacpp-gguf-sigfpe-dos
huntr-poc-bug06-llamacpp-gguf-sigfpe-dos is a machine learning model from Abhnv7. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
A crafted .gguf file with a tensor dimension ne[1] = 0 triggers an integer division-by-zero (INT64MAX / ne[1]) during GGUF parsing, crashing the process with SIGFPE before any model is loaded.
Downloads · 30 days
15
7% of all-time downloads
All-time downloads
206
Public
Repo size
—
Likes
0
Public
Click a slice to open those files.
.txt121 KB · 90%
From the Hugging Face model README
A crafted .gguf file with a tensor dimension ne[1] = 0 triggers an integer
division-by-zero (INT64_MAX / ne[1]) during GGUF parsing, crashing the process
with SIGFPE before any model is loaded.
gguf_init_from_readerpython3 generate_poc_bug06.py # writes poc_bug06.gguf (75 bytes)
./build/bin/llama-cli --model poc_bug06.gguf --n-predict 1
echo $? # 136 = 128 + SIGFPE(8)
Thread 1 received signal SIGFPE, Arithmetic exception at gguf.cpp:681
(gguf_init_from_reader). Full gdb backtrace in BUG06-actual-log.txt.
PoC SHA256: a46fbee54d38c8a7c4aac49aea75d6b0c412d4aa959ed5a3f9ae8d320891426d