ascendc
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses standard build and installation procedures for Ascend NPU development, including CMake for compilation and setuptools for Python packaging.
- [SAFE]: Environment setup is performed through standard CANN (Compute Architecture for Neural Networks) and Conda activation commands.
- [SAFE]: Dependencies are restricted to well-known libraries such as PyTorch and torch_npu, and the only external package installation is 'wheel' from the official Python registry.
- [SAFE]: No obfuscation, hidden URLs, or malicious redirection attempts were found in the templates or instructional content.
- [SAFE]: The skill includes explicit security and memory safety checks (Phase 10 Code Review and Phase 11 mssanitizer) to ensure the generated code is reliable and secure.
Audit Metadata