The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes Model Context Protocol (MCP) tools to perform administrative write and delete operations, such as modifying team roles, managing model allowlists, and deleting projects.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill processes external data from Scenario API responses, including member rosters (team_members_list), API key lists (api_keys_list), and consumption reports (usage).
Boundary markers: The instructions explicitly mandate human-in-the-loop verification, stating "confirm the exact names with the user" and "confirm the name and id from project_get first" before destructive actions.
Capability inventory: The skill has the capability to remove team members, delete projects, and revoke API keys through the scenario_tool_execute_delete tool.
Sanitization: There is no explicit description of sanitization or escaping for the data ingested from the external API before it is presented to the agent.
[EXTERNAL_DOWNLOADS]: The documentation references the official scenario-labs/skills GitHub repository for installation and management of related tools.

scenario-team-admin