fiftyone-dataset-inference

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill identifies requirements for external Python packages such as ultralytics, segment-anything, and open-clip-torch to support specific model architectures. These are well-known and trusted libraries within the machine learning community and are essential for the skill's primary functionality.
  • [COMMAND_EXECUTION]: The skill employs the execute_operator function to run pre-defined model inference tasks via the @voxel51/zoo/apply_zoo_model operator. This is a standard and expected operation within the FiftyOne ecosystem for applying models to datasets.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 07:02 PM