cube-explore-content
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documents an installation command for the Cube CLI that fetches a script from the vendor's official GitHub repository (
https://raw.githubusercontent.com/cube-js/cube/master/install-cli.sh) and pipes it to the shell. This is a standard installation procedure provided by the vendor for their tooling. - [COMMAND_EXECUTION]: The instructions include various CLI commands (e.g.,
cube workspace list,cube reports get) designed to interact with a Cube deployment. These commands are used for administrative discovery and inspection of workbooks, dashboards, and reports. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from a Cube workspace, such as report queries and content metadata. While this represents a data ingestion surface, the skill is limited to read-only inspection tasks, which minimizes the potential impact of instructions embedded in workspace data.
Audit Metadata