rdkit
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and scripts for the RDKit cheminformatics library. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected.
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the 'rdkit' package via 'uv' or 'conda-forge', which are standard, well-known, and trusted methods for Python environment management.
- [DATA_EXFILTRATION]: No sensitive file paths or unauthorized network operations were found. The skill specifically warns users about the security risks of using 'pickle' with untrusted data, recommending safer binary or text-based alternatives for molecular storage.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes external chemical data formats (SMILES, SDF, MOL), it lacks dangerous capabilities like shell execution or network exfiltration that could be exploited via malicious data payloads. The processing is limited to chemical informatics logic.
Audit Metadata