whatsapp-automation

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements an AI-powered chatbot that ingests untrusted messages from the WhatsApp API. This creates a surface for indirect prompt injection attacks where malicious users could potentially manipulate the AI's behavior.\n
  • Ingestion points: The n8n-nodes-base.whatsAppTrigger node in the n8n workflow example processes external user messages.\n
  • Boundary markers: There are no explicit delimiters or boundary markers separating user input from the system instructions in the provided n8n workflow example.\n
  • Capability inventory: The skill has access to sensitive tools including lookup_order, search_products, check_inventory, and create_ticket.\n
  • Sanitization: No sanitization or input validation is performed on the message content prior to processing by the AI model.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:18 AM