The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources that could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Data is ingested via search_guides and get_guide tools from the Ticket Fairy MCP server, as well as through CLI outputs when listing or retrieving order and ticket details.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious embedded content within the ingested data.
Capability inventory: The skill possesses capabilities to modify event settings, update ticket information, and process refunds via the ticketfairy CLI and the internal dashboard assistant (Fai).
Sanitization: No explicit sanitization or validation of the external content is mentioned before it is processed or presented to the user.
[COMMAND_EXECUTION]: The skill relies on the ticketfairy command-line interface to perform administrative tasks such as authenticating, listing brands, and updating event or ticket configurations.
[EXTERNAL_DOWNLOADS]: The instructions direct the user to install the official ticketfairy package from the NPM registry and connect to a remote MCP server hosted at https://www.ticketfairy.com/docs/mcp for guide retrieval.

manage-orders-and-refunds