The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown-based instructions and contains no executable scripts, binaries, or automated code execution patterns. It provides a structured documentation-driven approach to managing a third-party identity service.
[PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and process data from external sources, including Kinde Management API responses and multiple official documentation links. While this represents a theoretical surface for indirect prompt injection, the risk is mitigated by a multi-step workflow requiring explicit user authorization and state verification before any destructive or high-privilege mutations (such as organization deletion or user role changes) are performed. * Ingestion points: Workflow inventory in SKILL.md and external reference links in REFERENCES.md. * Boundary markers: The skill mandates specific 'Gate' checks where the agent must verify inventory status and mutation authorization. * Capability inventory: Interaction with the Kinde Management API for organization and user lifecycle operations. * Sanitization: The instructions assume standard platform-level safety filters for processing external content.

kinde-organizations