drug-admet-prediction
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses the
drugdiscMCP server to perform molecular property calculations. Analysis of the instructions and example data shows no evidence of command injection, network exfiltration, or unauthorized file access. - [SAFE]: Input data consists of SMILES strings (chemical notation) which are processed by the RDKit library. There are no signs of indirect prompt injection or malicious payloads within the provided examples.
Audit Metadata