zoho-crm-automation

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists entirely of Markdown documentation. It does not contain any Python scripts, Node.js packages, or shell commands.
  • [PROMPT_INJECTION] (SAFE): Indirect Prompt Injection Surface. The skill facilitates reading untrusted data from Zoho CRM (e.g., via ZOHO_SEARCH_ZOHO_RECORDS) and provides tools to modify data (e.g., ZOHO_CREATE_ZOHO_RECORD). While this creates an architectural surface for indirect prompt injection, there is no malicious implementation in the skill itself. 1. Ingestion points: ZOHO_SEARCH_ZOHO_RECORDS, ZOHO_GET_ZOHO_RECORDS. 2. Boundary markers: Absent. 3. Capability inventory: ZOHO_CREATE_ZOHO_RECORD, ZOHO_UPDATE_ZOHO_RECORD, ZOHO_CONVERT_ZOHO_LEAD. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:19 AM