The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a dynamic script generation pattern to interact with Uptime Kuma's administrative interface. It instructs the AI agent to copy a template script (scripts/socketio-client.mjs) to a temporary directory, modify its contents with logic for specific tasks (like adding or deleting monitors), and execute the resulting script using the bun runtime.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes data from external sources, specifically monitor names, URLs, and status messages from an Uptime Kuma instance. Because the skill can perform destructive actions like deleting monitors, a maliciously named monitor in a compromised or shared instance could attempt to influence the agent's behavior.
Ingestion points: Monitor metadata and status strings retrieved from the Prometheus /metrics endpoint and Socket.IO monitorList events as described in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands within the retrieved data are provided in the skill instructions.
Capability inventory: The skill provides capabilities to create, edit, pause, and delete monitors through Socket.IO events.
Sanitization: The skill does not define any sanitization or validation logic for the external strings before they are processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill documentation notes the requirement to install the socket.io-client package, which is a well-known library used for WebSocket communication.

uptime-kuma