run-promotions-and-discounts

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the official Ticket Fairy command-line interface from the npm registry.
  • Evidence: npm install -g ticketfairy in SKILL.md.
  • [COMMAND_EXECUTION]: The skill uses various shell commands to manage event promotions, authentication, and platform configuration via the vendor's official CLI tool.
  • Evidence: ticketfairy login, ticketfairy promotion list, and ticketfairy promotion delete commands defined in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for external content through the MCP search_guides and get_guide tools, which fetch documentation from the vendor's domain.
  • Ingestion points: MCP tool calls to https://www.ticketfairy.com/docs/mcp (SKILL.md).
  • Boundary markers: The skill instructs the agent to read guides before acting and provide suggested prompts for the 'Fai' assistant (SKILL.md).
  • Capability inventory: The skill can execute local CLI commands and manage platform resources (SKILL.md).
  • Sanitization: No explicit code-level sanitization is present in the markdown instructions, but safety is managed by human-in-the-loop requirements for all changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 05:38 PM