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

ai-for-science-oligoformer

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the OligoFormer source code from GitHub and model weights from Tsinghua University cloud storage. These downloads originate from reputable academic and open-source sources.\n- [COMMAND_EXECUTION]: Uses sed to automate the modification of source files for NPU compatibility. This includes injecting torch_npu imports and configuring environment variables required for Ascend hardware.\n- [SAFE]: The environment validation script uses dynamic importing on a fixed, hardcoded list of standard machine learning libraries to verify installation. This is a secure implementation with no external input influence.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:17 AM
Security Audit — agent-trust-hub — ai-for-science-oligoformer