deepchem
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data operations were detected. The skill follows established best practices for molecular machine learning and provides clear documentation for its capabilities. Analysis of the scripts confirms they are structured for legitimate data science tasks with standard parameter handling.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the DeepChem library to fetch pre-trained models from Hugging Face (such as ChemBERTa and MolFormer). These are well-known and standard sources for machine learning researchers, and the behavior is essential to the skill's primary function of enabling transfer learning. No unknown or untrusted download sources were identified.
Audit Metadata