follow-event-type-playbooks

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the official ticketfairy CLI tool from the npm registry. This is a standard operational procedure for the platform and originates from the official vendor.
  • [COMMAND_EXECUTION]: The skill provides numerous examples of shell commands for the ticketfairy CLI to perform administrative tasks such as creating tickets (ticketfairy ticket create), cloning events (ticketfairy event clone), and checking status (ticketfairy auth status). These commands are relevant to the skill's stated purpose and include recommendations for non-interactive output to suit agent environments.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external guides via a remote MCP server to determine task-specific workflows.
  • Ingestion points: The skill fetches guide content dynamically from https://www.ticketfairy.com/docs/mcp using tools like get_guide (SKILL.md).
  • Boundary markers: Explicit boundary markers for the fetched content are not defined in the instructions, although the skill follows a high-level step-by-step logic.
  • Capability inventory: The agent is authorized to execute a variety of CLI commands that can modify event data, issue tickets, and trigger emails to ticket holders (SKILL.md).
  • Sanitization: The skill uses standard placeholders (e.g., <EVENT_ID>) in its command templates and instructs the agent to wait for organizer confirmation before making any changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 05:38 PM