The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the official ticketfairy command-line tool to perform administrative tasks such as logging in, checking authentication status, and managing event data. These operations are performed with the user's permission and include safeguards like non-interactive mode requirements.
[EXTERNAL_DOWNLOADS]: The instructions direct the user to install the official Ticket Fairy CLI globally using npm install -g ticketfairy. This is a vendor-provided tool hosted on a well-known public registry.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, which creates a potential surface for indirect prompt injection.
Ingestion points: Data enters the agent context through attendee feedback comments, artist riders, tour books, email conversations, pasted spreadsheet rows, and various application forms (volunteers, traders, performers).
Boundary markers: The instructions do not explicitly specify the use of delimiters or 'ignore embedded instructions' warnings when processing this external content.
Capability inventory: The agent has the ability to execute shell commands via the ticketfairy CLI, send emails/messages to attendees and staff, and modify event records in the database.
Sanitization: There is no explicit mention of sanitization or filtering of external content before it is processed by the agent.

run-event-production