The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official Ticket Fairy CLI tool from the npm registry using npm install -g ticketfairy. This is a standard procedure for installing verified vendor tools from a well-known package registry.
[COMMAND_EXECUTION]: The instructions include various command-line operations for the ticketfairy CLI, such as authentication, brand management, and starting an MCP server. These commands are documented as part of the intended functionality for event organisers.
[INDIRECT_PROMPT_INJECTION]: The skill uses an external MCP server at https://www.ticketfairy.com/docs/mcp to fetch documentation and guides at runtime. This introduces a surface for processing untrusted external content.
Ingestion points: Content is fetched from https://www.ticketfairy.com/docs/mcp using the get_guide and search_guides tools.
Boundary markers: No specific delimiters or instructions to ignore embedded prompts are provided in the skill text for the fetched guide data.
Capability inventory: The agent has the ability to execute CLI commands and provides prompts for an internal assistant ("Fai") within the dashboard.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the external guides before it is processed by the agent.
[SAFE]: The skill incorporates several security best practices, including explicit instructions to keep secrets out of chat, requiring human confirmation before performing any destructive or state-changing actions, and directing all payment-related tasks to the browser checkout to prevent financial data exposure.

run-door-check-in