whatsapp-automation
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the user to connect to an external MCP server at https://rube.app/mcp. This server provides the tools necessary for WhatsApp automation and represents an external dependency outside of trusted well-known services.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to the processing of external data and the availability of powerful tool capabilities.
- Ingestion points: The skill retrieves data from the WhatsApp API via tools such as WHATSAPP_GET_MESSAGE_TEMPLATES, WHATSAPP_GET_MEDIA, and WHATSAPP_GET_BUSINESS_PROFILE.
- Boundary markers: There are no instructions for the agent to use specific delimiters or boundary markers when handling data from these external tools.
- Capability inventory: The skill can perform significant write operations including WHATSAPP_SEND_MESSAGE, WHATSAPP_SEND_TEMPLATE_MESSAGE, WHATSAPP_SEND_MEDIA, and WHATSAPP_CREATE_MESSAGE_TEMPLATE.
- Sanitization: No sanitization, validation, or escaping of external content is specified before interpolation into agent prompts.
- [NO_CODE]: The skill consists solely of a markdown file with instructions and does not include any executable scripts or code files, which mitigates the risk of direct malicious code execution on the local system.
Audit Metadata