track-advertising-campaigns
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands using the official
ticketfairyCLI for authentication, brand management, and retrieving event statistics.\n- [EXTERNAL_DOWNLOADS]: The skill guides the user to install the vendor's official CLI package (ticketfairy) from the NPM registry.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external documentation and platform statistics, creating a surface for potential instruction injection.\n - Ingestion points: Documentation content retrieved from the vendor's MCP server at
https://www.ticketfairy.com/docs/mcpand event-specific statistics returned by the CLI.\n - Boundary markers: No explicit delimiters or instructions are used to isolate external content from the agent's primary instructions.\n
- Capability inventory: The agent can execute CLI commands, interact with the platform's brand and event settings, and manage tracking configurations.\n
- Sanitization: There is no mention of sanitizing or validating content retrieved from external guides or event data before it is processed by the agent.
Audit Metadata