skills/open-edge-platform/physical-ai-studio/physicalai-train-working-with-datasets/Gen Agent Trust Hub
physicalai-train-working-with-datasets
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches machine learning datasets from HuggingFace, a well-known service, using the
repo_idparameter (e.g.,lerobot/pusht) within theLeRobotDataModuleconfiguration. These downloads are standard for the skill's documented purpose of training AI policies. - [COMMAND_EXECUTION]: The skill uses the
physicalaiCLI anduvpackage runner to execute training tasks and run unit tests. These tools are project-specific utilities intended for development and training workflows. - [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for ingesting external data via dataset repositories. While datasets are untrusted external inputs, the skill's primary function is to facilitate this data flow for training, and no exploitable capabilities (like unauthorized file writes or exfiltration) are exposed through this ingestion.
Audit Metadata