The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the agkan CLI utility to retrieve and manage task lists and details.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it interpolates untrusted task titles and bodies into sub-agent prompts. Ingestion points: Task data is retrieved via agkan task list and agkan task get. Boundary markers: Task content is included directly without delimiters or guardrail instructions to ignore nested directives. Capability inventory: The skill and its sub-agents can execute shell commands via agkan. Sanitization: No filtering or sanitization of the backlog task content is performed.

agkan-planning