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
Risk Level
SAFE
Analyzed
Jun 27, 2026, 11:42 AM
Security Audit — agent-trust-hub — datamol