zoho-crm-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves data from Zoho CRM modules (such as Leads or Contacts) which are frequently populated with external, untrusted content. This retrieved content is subsequently used in workflows that include high-capability write operations like record updates and lead conversions.
- Ingestion points:
ZOHO_SEARCH_ZOHO_RECORDSandZOHO_GET_ZOHO_RECORDSreferenced inSKILL.md. - Boundary markers: No explicit instructions provided to the agent to treat retrieved record data as untrusted or to use delimiters.
- Capability inventory:
ZOHO_CREATE_ZOHO_RECORD,ZOHO_UPDATE_ZOHO_RECORD, andZOHO_CONVERT_ZOHO_LEAD(found inSKILL.md). - Sanitization: No sanitization or validation steps are defined for the ingested CRM data.
- [EXTERNAL_DOWNLOADS]: The setup instructions require the configuration of an external MCP server endpoint (
https://rube.app/mcp). This configuration establishes a connection where CRM data and tool execution logic are processed via third-party infrastructure.
Audit Metadata