AGENT LAB: SKILLS

helpdesk-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (LOW): The skill provides instructions for tools that ingest untrusted data from external HelpDesk tickets, creating a surface for indirect prompt injection.
  • Ingestion points: Ticket content retrieved via HELPDESK_LIST_TICKETS and HELPDESK_LIST_CANNED_RESPONSES.
  • Boundary markers: No delimiters or instructions are provided to the agent to treat external ticket data as untrusted.
  • Capability inventory: The skill utilizes read-only tools for listing and browsing ticketing data.
  • Sanitization: No sanitization or validation steps are mentioned in the workflow.
  • [External Downloads] (LOW): The setup instructions direct the user to add an external MCP server at https://rube.app/mcp. While this is a configuration for the stated service provider, the domain is not on the trusted external source list.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:06 PM