skills/ascend-ai-coding/awesome-ascend-skills/external-cannbot-model-model-infer-fusion/Gen Agent Trust Hub
external-cannbot-model-model-infer-fusion
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python utility script
scripts/torch_npu_query.pydesigned to be executed by the agent to query localtorch_npuAPI documentation. This is a legitimate development tool. - [SAFE]: The skill references official Huawei Ascend documentation and repositories on
hiascend.comandgitcode.com/Ascend. These are well-known, trusted vendor sources for Ascend NPU development. - [SAFE]: The core functionality focuses on pattern matching and code transformation to improve model inference performance using standard
torch_npufusion operators. - [SAFE]: No evidence of data exfiltration, credential exposure, or malicious persistence mechanisms was found. The logic is transparently implemented for developer productivity.
Audit Metadata