deepchem

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWEXTERNAL_DOWNLOADS
Full Analysis
  • [External Downloads] (LOW): Both scripts utilize the deepchem.molnet module (e.g., load_tox21, load_delaney), which automatically downloads datasets from DeepChem's AWS S3 infrastructure if they are not found locally. This is standard research behavior but involves unverified external downloads.\n- [Indirect Prompt Injection] (LOW): The scripts feature a data ingestion surface via the --data CSV argument.\n
  • Ingestion points: Custom data is loaded through dc.data.CSVLoader in both scripts.\n
  • Boundary markers: Absent (typical for CSV processing scripts).\n
  • Capability inventory: No high-risk capabilities such as arbitrary command execution, network exfiltration of local files, or code execution were identified.\n
  • Sanitization: Input strings are parsed into chemical representations by the DeepChem library, minimizing the risk of instructions affecting control flow.\n- [Data Exposure & Exfiltration] (SAFE): No evidence of hardcoded credentials or unauthorized data exfiltration was found. The scripts operate on local files and trusted benchmark data sources.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 01:37 PM