zoho-crm-automation
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill requires the user to configure a third-party MCP server endpoint.
- Evidence: The setup instructions direct the user to add
https://rube.app/mcpas an MCP server. This domain is not part of the pre-approved trusted organizations or repositories list. This finding is downgraded to LOW as it is the primary intended mechanism of the skill. - PROMPT_INJECTION (LOW): The skill exhibits a surface for indirect prompt injection by ingesting data from Zoho CRM records.
- Ingestion points: Data enters the agent context via
ZOHO_SEARCH_ZOHO_RECORDSandZOHO_GET_ZOHO_RECORDStools. - Boundary markers: Absent. There are no instructions provided to the agent to treat data retrieved from the CRM as untrusted or to ignore embedded instructions within record fields.
- Capability inventory: The skill possesses significant write capabilities, including
ZOHO_CREATE_ZOHO_RECORD,ZOHO_UPDATE_ZOHO_RECORD, andZOHO_CONVERT_ZOHO_LEAD(which is an irreversible action). - Sanitization: Absent. No logic is defined to sanitize or validate record content before it is processed or used to influence subsequent agent actions.
Audit Metadata