freshservice-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The setup process involves adding an external MCP server endpoint (https://rube.app/mcp) to the client configuration. This is the intended delivery mechanism for the skill's capabilities.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from Freshservice tickets.
  • Ingestion points: Data is ingested through tools like FRESHSERVICE_LIST_TICKETS and FRESHSERVICE_GET_TICKET (specifically description and conversations).
  • Boundary markers: The instructions do not define boundary markers or 'ignore embedded instructions' directives when processing these data fields.
  • Capability inventory: The agent has write access to Freshservice via FRESHSERVICE_CREATE_TICKET, FRESHSERVICE_BULK_UPDATE_TICKETS, and FRESHSERVICE_CREATE_TICKET_OUTBOUND_EMAIL.
  • Sanitization: No input sanitization, escaping, or validation steps are prescribed for the ingested content before the agent acts upon it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — freshservice-automation