The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the omni CLI to perform administrative tasks. This involves executing local commands based on user intent and parameters. The instructions provide safeguards such as verifying the CLI installation and checking active profiles before execution.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes data from external sources.
Ingestion points: Reads data from Omni SCIM API (users, groups), document/folder permission lists, and CSV file uploads via omni uploads.
Boundary markers: The instructions do not define specific delimiters for separating external data from agent instructions.
Capability inventory: The skill can create, update, and delete users, groups, permissions, and schedules, and rotate security keys using the omni CLI.
Sanitization: No explicit sanitization or filtering of API responses or CSV content is mentioned before the agent processes the information.
[SAFE]: External references are limited to official documentation and the vendor's own GitHub repository (e.g., github.com/exploreomni/cli), which are trusted sources for this skill's context.

omni-admin