nlq-dashboard-orchestrator
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were detected in the skill instructions or reference files.
- [PROMPT_INJECTION]: The skill maintains a clear, goal-oriented instruction set without any attempts to override system prompts, bypass safety filters, or use role-play for restricted behavior.
- [DATA_EXFILTRATION]: While the skill handles connection details for BI reporting, it does so through a legitimate user-driven workflow. There are no hardcoded credentials, sensitive file path accesses, or network calls to untrusted domains.
- [COMMAND_EXECUTION]: The skill coordinates local file system operations within designated project folders (
generated-reports/,generated-dashboards/). No arbitrary command execution or privilege escalation attempts were found. - [REMOTE_CODE_EXECUTION]: The skill orchestrates existing internal tools and does not download or execute scripts from remote or unverifiable sources.
- [SAFE]: The inclusion of 'Gate A' and 'Gate B' as mandatory user-confirmation steps serves as a robust defense against unintended actions, ensuring the user reviews the data model and dashboard plan before generation begins.
Audit Metadata