run-door-check-in
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the vendor's official CLI package ('ticketfairy') from the NPM registry and connect to an MCP server hosted on the vendor's domain ('ticketfairy.com'). These are legitimate vendor resources.
- [COMMAND_EXECUTION]: The skill utilizes the 'ticketfairy' command-line interface to perform administrative tasks such as checking status, listing brands, and viewing check-in aggregates.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data including attendee names, email addresses, and session descriptions, which represents a potential injection surface. However, this risk is mitigated by explicit instructions requiring human-in-the-loop approval for all significant actions and strict guidelines against handling credentials within the conversation. 1. Ingestion points: Attendee data, session details, and order info retrieved from Ticket Fairy API. 2. Boundary markers: Not explicitly present in data fields, but mitigated by process instructions. 3. Capability inventory: CLI tool execution and MCP server interactions. 4. Sanitization: Not explicitly implemented in code, relying on human oversight.
Audit Metadata