rudder-data-graphs
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the rudder-cli via the Bash tool to execute 'workspace accounts list --json'. This is a legitimate administrative action to retrieve the warehouse account ID necessary for the Data Graph YAML and is permitted by the allowed-tools configuration.
- [DATA_EXFILTRATION]: The skill reads workspace metadata and source configurations to produce an inventory and draft graph models. This data is handled within the agent's context for generating deliverables; no unauthorized network activity was detected.
- [PROMPT_INJECTION]: No patterns attempting to bypass safety protocols or override system instructions were found.
- [SAFE]: The skill adheres to legitimate vendor workflows for RudderStack workspace management and provides well-documented references for its operations.
Audit Metadata