skills/grafana/gcx/import-dashboards/Gen Agent Trust Hub

import-dashboards

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests dashboard data from external Grafana instances via the gcx dev import command. Ingestion points: Dashboard resources are fetched via the K8s API /apis endpoint (SKILL.md). Boundary markers: The workflow includes a manual 'Review and edit' step (SKILL.md), though no programmatic delimiters are defined for the imported content. Capability inventory: The skill writes generated Go code to the local file system and instructs the user to execute it using go run .. Sanitization: Relies on the gcx tool's internal converter and manual user oversight.
  • [DYNAMIC_EXECUTION]: The skill generates Go source code from imported dashboard data and executes it using go run .. This is a standard and supported workflow for the Grafana-as-Code pattern.
  • [COMMAND_EXECUTION]: The skill utilizes official vendor tools including the gcx CLI and the go toolchain to manage resources and build manifests, which is appropriate for the stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:08 AM
Security Audit — agent-trust-hub — import-dashboards