Live › vulnerability › CVE-2026-112107
Go to dashboardfastllm, an LLM inference library, has a buffer overflow in its Safetensors weight loader when a model file sets a crafted data_offsets value. An attacker who gets a team to load a malicious model file can likely corrupt memory and may run code on the host.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-23 21:57 UTC. All times on this page are UTC.
Teams that run fastllm 1.8.2 or earlier and load Safetensors model files, especially files downloaded from public hubs or supplied by users. Systems that only serve models from a fixed, internally vetted set are less exposed. Teams that do not use fastllm can skip it.
No product ranges from the sources yet.
fastllm in dependency files and build configs.<= 1.8.2.Each row is the first time that source carried this signal. The analyst’s rows are its own findings.
A flaw has been found in ztxz16 fastllm up to 1.8.2. Affected by this issue is the function SafeTensorItem::CreateBuffer of the file src/model.cpp of the component Safetensors Weight Loading. This manipulation of the argument data_offsets causes buffer overflow. The attack can be initiated remotely. The exploit has been published and may be used. The project was informed of the problem early through an issue report but has not responded yet.
This page as .md · .json · in your agent: get_signal("CVE-2026-112107")
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.