The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes kubectl for Kubernetes resource management and grafana-cli for Grafana administration. This includes instructions for retrieving the Grafana administrative password from Kubernetes secrets.
[EXTERNAL_DOWNLOADS]: The skill references and fetches Helm charts from the official Grafana repository at https://grafana.github.io/helm-charts for deployment purposes.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process Grafana Dashboard JSON and PromQL queries from potentially untrusted external or community sources.
Ingestion points: Processes dashboard configurations and templates which may be sourced from community repositories or provided by the user.
Boundary markers: The instructions do not define specific delimiters or security guardrails for handling untrusted JSON content.
Capability inventory: The agent has access to file modification tools (Write, Edit) and system-level command execution (kubectl, grafana-cli).
Sanitization: No explicit sanitization or validation routines are described for the ingestion of dashboard data.

grafana-expert