signoz-creating-dashboards
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows secure design principles for AI agent extensions. It utilizes a specific set of MCP tools (
signoz_*) and explicitly forbids falling back to raw HTTP calls or shell commands. - [SAFE]: Data handling is restricted to observability metadata (dashboard IDs, metric names, and panel configurations) within the SigNoz ecosystem. No hardcoded credentials or unauthorized access to sensitive files were found.
- [SAFE]: The workflow includes mandatory user checkpoints: checking for existing dashboards to prevent clutter and requiring confirmation before any write operations.
- [SAFE]: For custom dashboard builds, the skill mandates a dry-run of queries using
signoz_execute_builder_queryto validate syntax and data availability before the dashboard is saved, preventing the creation of broken or empty dashboards.
Audit Metadata