helpdesk-automation
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server endpoint at
https://rube.app/mcpto function. This is a legitimate requirement for the stated purpose of connecting to the Rube MCP/Composio toolkit. - [INDIRECT_PROMPT_INJECTION]: The skill defines workflows that ingest external data from HelpDesk tickets and canned responses, creating a potential surface for indirect prompt injection.
- Ingestion points: Data is retrieved through the
HELPDESK_LIST_TICKETSandHELPDESK_LIST_CANNED_RESPONSEStools (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or specific safety markers when the agent processes or displays ticket content.
- Capability inventory: The skill provides tools for connection management (
RUBE_MANAGE_CONNECTIONS) and ticket browsing (HELPDESK_LIST_TICKETS). - Sanitization: No specific content sanitization or validation logic is defined for the ticket data retrieved from the external service.
Audit Metadata