datamol
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill supports reading molecular data files from remote HTTP/HTTPS URLs and cloud storage providers like AWS S3 and Google Cloud Storage (GCS) using the fsspec library. This is a standard and documented feature for handling large-scale chemical datasets.
- [DATA_EXFILTRATION]: Functions such as to_sdf and to_xlsx allow saving processed data to remote cloud storage. This is a standard capability for data analysis workflows and is used for saving scientific results rather than unauthorized data transfer.
- [COMMAND_EXECUTION]: The skill utilizes parallel processing (e.g., in read_sdf and cluster_mols) via the n_jobs parameter, which leverages standard Python multiprocessing for computational efficiency. No evidence of arbitrary shell command execution or unsafe subprocess calls was found.
- [SAFE]: The skill utilizes a well-established library and follows standard practices for cheminformatics. Analysis of the instructions and reference documentation reveals no prompt injection attempts, obfuscation, or persistence mechanisms.
Audit Metadata