whatsapp-automation
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface
- Ingestion points: The skill processes incoming messages from the WhatsApp API through the
whatsAppTriggerandParse Messagenodes in the n8n workflow (SKILL.md). - Boundary markers: The system prompt provided for the AI chatbot does not include explicit delimiters or instructions to ignore potentially malicious commands embedded in user-supplied message text (
SKILL.md). - Capability inventory: The chatbot is equipped with capabilities to send messages, lookup orders, search products, and create support tickets using tools like
whatsapp_send_messageandlookup_order(SKILL.md). - Sanitization: The provided workflow logic focuses on message parsing but does not explicitly detail sanitization or validation of the message body before it is interpolated into the AI's processing context (
SKILL.md).
Audit Metadata