biomni
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches approximately 11GB of integrated biomedical databases and literature from Stanford University and HuggingFace repositories during initialization.
- [COMMAND_EXECUTION]: Documents an autonomous agent capability that generates and executes Python analysis code with system privileges. The skill includes appropriate security disclosures, recommending execution within isolated environments like Docker or VMs to mitigate risks.
- [SAFE]: No malicious patterns, such as obfuscation, credential exfiltration, or persistence mechanisms, were detected in the skill instructions or metadata.
Audit Metadata