freshservice-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes ticket data, including subjects and descriptions, which are sources of untrusted external content. This creates a surface where embedded instructions in tickets could theoretically influence agent behavior.
- Ingestion points:
FRESHSERVICE_LIST_TICKETSandFRESHSERVICE_GET_TICKETtools defined inSKILL.mdretrieve ticket content. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore content within ticket fields.
- Capability inventory: The skill has capabilities to create and update tickets, perform bulk operations, and send outbound emails via
FRESHSERVICE_CREATE_TICKET,FRESHSERVICE_BULK_UPDATE_TICKETS, andFRESHSERVICE_CREATE_TICKET_OUTBOUND_EMAIL. - Sanitization: No explicit sanitization or filtering of retrieved ticket content is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill references external resources for functionality and documentation.
- References the Composio toolkit documentation at
https://composio.dev/toolkits/freshservice. - Instructs the user to add the MCP server endpoint
https://rube.app/mcpin their client configuration.
Audit Metadata