rdkit
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- Data Exposure & Exfiltration (SAFE): The scripts only interact with local molecular data files (SDF, SMILES, CSV) provided via command-line arguments. No access to sensitive system directories or network communication was detected.\n- Unverifiable Dependencies & Remote Code Execution (SAFE): The scripts depend on RDKit, a standard industry library. No dynamic code execution (eval/exec) or piped remote installations were found.\n- Indirect Prompt Injection (SAFE): While the skill ingests external SMILES strings and molecule files, these are processed strictly as chemical structures by the RDKit parser. There is no path for these inputs to be interpreted as agent instructions.
Audit Metadata