medchem

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the 'medchem' and 'datamol' Python packages, which are installed from standard package registries. These are legitimate tools in the scientific community.
  • [COMMAND_EXECUTION]: The provided script 'scripts/filter_molecules.py' performs file system operations to read chemical data and write filtered results. These actions are within the expected scope of the skill's functionality.
  • [PROMPT_INJECTION]: The skill processes external molecular data formats (SMILES, CSV, SDF). While this represents a potential surface for indirect prompt injection, the data is validated and parsed into molecular structures by the 'datamol' library, which mitigates the risk of command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 07:58 PM