Answer in brief
CVE-2026-108960 records a Medium severity (CVSS 4.8) vulnerability in Tiiny-AI PowerInfer FFN GPU-split Loader ggml-cuda.cu create_striped_mat_to_gpu out-of-bounds. The current sources do not mark it as known exploited. The current feed maps Tiiny-AI/PowerInfer (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 4.8. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps Tiiny-AI/PowerInfer (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| Tiiny-AI/PowerInfergeneric | 8bd56d69906c9d2dba4d3bf6899763401e01a9a4 | Not reported |
Published upstream
Oct 13, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Oct 13, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Oct 13, 2026
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.
Quoted source text, attributed separately from HOL analysis.