helpdesk-automation

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server at https://rube.app/mcp.
  • [PROMPT_INJECTION]: The skill processes untrusted ticket data and responses, creating a surface for indirect prompt injection. Risk is mitigated by the read-only nature of the current toolset.
  • Ingestion points: HELPDESK_LIST_TICKETS and HELPDESK_LIST_CANNED_RESPONSES tools.
  • Boundary markers: Absent.
  • Capability inventory: Read-only listing tools (listing tickets, views, canned responses, and custom fields).
  • Sanitization: Absent.
  • [NO_CODE]: No local code or scripts are included in this skill; it consists entirely of instructions and configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:59 AM