Downloads · 30 days
4
3% of all-time downloads
oguzhanakkaya/poc-wavtokenizer-posnet-oob-gguf
poc-wavtokenizer-posnet-oob-gguf is a machine learning model from oguzhanakkaya. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository contains a deliberately-malformed GGUF file that triggers an out-of-bounds access in llama.cpp's wavtokenizer-dec model loader.
Downloads · 30 days
4
3% of all-time downloads
All-time downloads
116
Public
Repo size
—
Likes
0
Public
Click a slice to open those files.
.gguf36.3 KB · 87%
From the Hugging Face model README
This repository contains a deliberately-malformed GGUF file that triggers
an out-of-bounds access in llama.cpp's wavtokenizer-dec model loader.
The wavtokenizer-dec.posnet.block_count and wavtokenizer-dec.convnext.block_count
GGUF metadata keys are read without any upper-bound validation against the
base block_count (n_layer_all). This causes dev_layer.at(il) to throw
std::out_of_range when the loader tries to create tensors for posnet/convnext
layers beyond the allocated range.
Attacker-controlled GGUF metadata → crash on model load (DoS).
llama-cli -m poc_wavtokenizer_posnet_oob.gguf -n 1 -p "a"
# -> vector::_M_range_check: __n (which is 1) >= this->size() (which is 1)
python3 poc_wavtokenizer_posnet_oob.py
Reported via huntr MFV program. This is a sibling bug to the n_layer_all
fix merged in llama.cpp PR #26051 — the base block_count was bounded but
posnet.block_count and convnext.block_count were missed.