The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the superplane CLI to interact with the SuperPlane platform. Commands include listing canvases, events, and executions, as well as destructive actions like canceling executions or deleting items from a queue.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from workflow execution logs and payloads.
Ingestion points: Workflow execution history, node payloads, and error messages are retrieved via superplane executions list -o yaml and superplane events list-executions (SKILL.md).
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the documentation.
Capability inventory: The agent can list, cancel, and delete executions and queue items, as well as update canvases (SKILL.md).
Sanitization: No sanitization or validation of the ingested execution data is described.
[EXTERNAL_DOWNLOADS]: The skill references official documentation and installation guides hosted on docs.superplane.com. These are vendor-owned resources and are considered safe sources for configuration and guidance.

superplane-monitor