grow-sales-with-referrals

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Instructs the agent to install the ticketfairy command-line utility globally via npm install -g ticketfairy. This is the official tool provided by the skill's author.\n- [COMMAND_EXECUTION]: Utilizes the ticketfairy CLI to perform administrative tasks such as checking authentication status, listing brands, and managing referral prizes. All commands are intended for use with organiser permission.\n- [INDIRECT_PROMPT_INJECTION]: The skill retrieves guide content and instructions from the official Ticket Fairy MCP server at https://www.ticketfairy.com/docs/mcp.\n
  • Ingestion points: Untrusted data enters the agent context through the search_guides and get_guide tools (SKILL.md).\n
  • Boundary markers: The instructions do not define specific delimiters or guardrails for processing the retrieved guide content.\n
  • Capability inventory: The skill allows for local command execution via the Ticket Fairy CLI and the generation of prompts for the dashboard assistant.\n
  • Sanitization: No automated sanitization of the fetched guide content is described.\n- [CREDENTIALS_UNSAFE]: While the skill mentions the TICKET_FAIRY_API_KEY, it explicitly instructs the user to store it securely in an environment variable and warns the agent never to request or transmit sensitive tokens in the chat.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 10:46 PM