databricks-aibi-dashboards
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation and instruction for managing Databricks AI/BI dashboards using the official databricks CLI tools. Analysis of the provided scripts, instructions, and reference materials reveals no malicious behavior, hardcoded secrets, or unauthorized network operations. All functionality is consistent with the stated purpose of dashboard development within the Databricks ecosystem.\n- [COMMAND_EXECUTION]: The skill instructs the agent to use the databricks CLI for tasks such as listing warehouses, querying tables, and deploying dashboard JSON. These commands are standard operations for Databricks workspace management and are used according to best practices, such as testing queries before deployment.\n- [PROMPT_INJECTION]: The skill processes table schemas and query results to design dashboard widgets, which represents a surface for indirect prompt injection.\n
- Ingestion points: Data schema and query results obtained from Databricks tables via the discover-schema and query CLI tools (SKILL.md).\n
- Boundary markers: Not present. The instructions do not specify the use of delimiters when providing external data to the agent context.\n
- Capability inventory: The skill has the capability to execute SQL queries and deploy workspace resources (dashboards) via the CLI (SKILL.md).\n
- Sanitization: No explicit sanitization or validation of data retrieved during the discovery process is documented.
Audit Metadata