bio-admet-prediction
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses established chemical informatics libraries (RDKit, DeepChem) for its primary functionality.
- [EXTERNAL_DOWNLOADS]: The skill makes legitimate API calls to 'https://admetlab3.scbdd.com/api/predict', which is the official endpoint for the ADMETlab 3.0 service described in the skill's purpose.
- [COMMAND_EXECUTION]: Code examples include standard library imports and subprocess-free Python scripts for molecular property calculation and filtering.
- [DATA_EXFILTRATION]: No evidence of sensitive file access or unauthorized data transmission was found. The network activity is limited to sending SMILES strings (chemical identifiers) to a specialized scientific API for prediction.
Audit Metadata