NYC
skills/ovachiever/droid-tings/geniml/Gen Agent Trust Hub

geniml

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): No malicious patterns, prompt injections, or unauthorized data access commands were detected across the five documentation files.
  • EXTERNAL_DOWNLOADS (SAFE): The skill references the StarSpace repository from 'facebookresearch' and pre-trained models from Hugging Face ('databio' namespace). Both sources are considered trusted according to the security guidelines.
  • COMMAND_EXECUTION (SAFE): CLI examples for 'geniml', 'uniwig', and standard shell commands ('cat') are appropriate for the library's intended genomic processing purpose.
  • DATA_EXFILTRATION (SAFE): The 'BBClient' utility for caching remote BED files is a standard performance optimization for genomic data access and does not exhibit exfiltration behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:55 PM