The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the okou CLI binary to manage the lifecycle of workflows and triggers. Supported operations include okou workflow create, edit, view, run, delete, and copy, as well as okou workflow trigger add, update, enable, disable, and remove.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by processing untrusted data from multiple external integrations.
Ingestion points: As detailed in references/trigger-setup.md, the skill ingests data from external sources through gmail-new-message, gmail-label-applied, github-label-applied, google-forms-response-submitted, and webhook payloads.
Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate incoming external data from the agent's internal reasoning.
Capability inventory: The agent has the capability to modify persistent system behavior by creating or updating automations that run on schedules or event triggers across the okou environment.
Sanitization: There is no evidence of specific data sanitization, filtering, or validation processes for the content retrieved from external triggers before it is used by the agent.

workflow-setup