freshservice-automation

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill integrates with a remote MCP server hosted at https://rube.app/mcp, which serves as the provider for the Freshservice automation tools.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting untrusted data and having high-privilege capabilities.
  • [PROMPT_INJECTION]: Ingestion points: Reads ticket subjects, descriptions, and other metadata via FRESHSERVICE_LIST_TICKETS and FRESHSERVICE_GET_TICKET tools.
  • [PROMPT_INJECTION]: Boundary markers: No delimiters or instructions are provided to the agent to isolate external data from instructions.
  • [PROMPT_INJECTION]: Capability inventory: Possesses tools for ticket modification (FRESHSERVICE_BULK_UPDATE_TICKETS) and outbound communication (FRESHSERVICE_CREATE_TICKET_OUTBOUND_EMAIL).
  • [PROMPT_INJECTION]: Sanitization: No input validation or data sanitization mechanisms are described for the processed ticket data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 11:32 AM