cube-build-model
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the Cube CLI installation script from the vendor's official GitHub repository at
raw.githubusercontent.com/cube-js/cube.- [COMMAND_EXECUTION]: Executes shell commands via thecubeCLI to perform operations such as authentication, project deployment, and semantic model management.- [INDIRECT_PROMPT_INJECTION]: - Ingestion points: Reads semantic model YAML files and deployment metadata through
cube:readDataModelFileandcube data-model list. - Boundary markers: The instructions do not define specific delimiters to isolate external model content from the agent's logic.
- Capability inventory: Provides capabilities for file writing (
cube:writeDataModelFile), command execution, and deployment to cloud environments. - Sanitization: Content from the semantic model files is processed without explicit sanitization steps mentioned in the skill.
Audit Metadata