Skills
skills/ascend-ai-coding/awesome-ascend-skills/ai-for-science-ai4s-basic/Gen Agent Trust Hub

ai-for-science-ai4s-basic

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill follows established best practices for NPU model migration.
  • [COMMAND_EXECUTION]: The skill uses standard CLI utilities including npu-smi for hardware status, rg (ripgrep) and find for code analysis, and pip for package management. These tools are used appropriately within the context of model migration and environment auditing.
  • [EXTERNAL_DOWNLOADS]: The instructions reference the official Huawei Cloud PyPI mirror (repo.huaweicloud.com) for dependency resolution and the well-known PyTorch Geometric (rusty1s) GitHub repositories for source-based compilation of required extensions. These are trusted and established sources within the AI development ecosystem.
  • [DYNAMIC_IMPORT]: The diagnostic script scripts/check_npu_basics.py utilizes importlib.import_module to verify the installation of torch and torch_npu. The module names are provided as static string literals, which is a standard and safe method for runtime environment validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:16 AM
Security Audit — agent-trust-hub — ai-for-science-ai4s-basic