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
Risk Level
SAFE
Analyzed
Apr 1, 2026, 05:35 AM
Security Audit — agent-trust-hub — whatsapp-automation