The Agent Skills Directory

[SAFE]: No security issues detected. The skill follows established best practices for Grafana dashboard management and limits its operations to the vendor-provided gcx utility and official API endpoints.
[INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for processing existing dashboard data, but this is a core requirement for its primary function.
Ingestion points: Existing dashboard JSON is retrieved and stored in /tmp/similar-dashboard.json (SKILL.md, Step 2).
Boundary markers: None explicitly defined for the data used to inform new dashboard design.
Capability inventory: gcx resources push, gcx api, and gcx dashboards snapshot (SKILL.md).
Sanitization: The skill uses jq to extract specific, structured data fields (e.g., .expr, .spec.templating.list) which significantly limits the potential for interpreting arbitrary text as instructions.

create-dashboard