grafana-dashboards

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as metric names, labels, and namespaces to generate Grafana dashboard JSON and configuration files (Terraform/Ansible).
  • Ingestion points: User-provided inputs for metrics and filtering labels are interpolated into dashboard templates throughout SKILL.md and referenced in resources/implementation-playbook.md.
  • Boundary markers: Absent. The instructions do not define specific delimiters or warnings to ignore potential instructions embedded in metric metadata.
  • Capability inventory: The skill facilitates the creation and deployment of configuration files to the file system (via Ansible) and potentially remote Grafana instances (via Terraform).
  • Sanitization: While the playbook explicitly advises avoiding secrets in exported JSON, there is no defined validation or escaping mechanism for external content used in query expressions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 06:32 AM
Security Audit — agent-trust-hub — grafana-dashboards