CVE-2026-108960 Tiiny-AI PowerInfer FFN GPU-split Loader ggml-cuda.cu create_striped_mat_to_gpu out-of-bounds
A local attacker can trigger an out-of-bounds read in the GPU loader, potentially causing information disclosure or crashes.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-108960?
CVE-2026-108960 is a medium-severity memory corruption vulnerability in Tiiny-AI PowerInfer, published on 13 Oct 2026. It can only be exploited from the same machine or local network, with no action from the victim.
Official description
A vulnerability was detected in Tiiny-AI PowerInfer up to 8bd56d69906c9d2dba4d3bf6899763401e01a9a4. Affected is the function create_striped_mat_to_gpu of the file smallthinker/ggml/src/ggml-cuda/ggml-cuda.cu of the component FFN GPU-split Loader. The manipulation results in out-of-bounds read. The attack needs to be approached locally. The exploit is now public and may be used. This product utilizes a rolling release system for continuous delivery, and as such, version information for affected or updated releases is not disclosed. The pull request to fix this issue awaits acceptance.
Which versions are affected by CVE-2026-108960?
How do I fix CVE-2026-108960?
No fix has been published for CVE-2026-108960 yet. Limit exposure of the affected software until one is available.
Upgrade to the fixed version. Memory-safe languages, compiler hardening and fuzzing prevent most new cases. More about Memory corruption.
Is CVE-2026-108960 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-108960 exists.
Sources
Also known as GHSA-p4fx-7pm7-23jr.