The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell utilities including curl, jq, and date to perform API requests and process responses. These commands are necessary for the skill's primary function of interacting with the Grafana API.
[EXTERNAL_DOWNLOADS]: The skill makes network requests to the GRAFANA_URL provided by the user to fetch dashboard configurations, alert rules, and telemetry data. This interaction is consistent with the intended purpose of managing a well-known service.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection (Category 8) because it interpolates potential user-supplied data into shell commands.
Ingestion points: Dashboard UIDs, Prometheus query strings, and annotation metadata in SKILL.md are points where untrusted data could enter the agent context.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the command templates.
Capability inventory: The skill possesses network communication capabilities via curl and data processing via jq across all examples in SKILL.md.
Sanitization: There is no evidence of input sanitization or escaping for the interpolated variables in the provided shell snippets.

grafana