dashboard-build
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: No malicious patterns, such as prompt injection or unauthorized data exfiltration, were detected. The skill is a legitimate productivity tool.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts via the
uvtool. This is necessary for fetching model schemas and running the dashboard application for preview and testing. - [EXTERNAL_DOWNLOADS]: The skill references the
vizrolibrary and other common data science packages likepandasandplotly. These are downloaded from official package registries, which is standard behavior for Python-based development skills.
Audit Metadata