whatsapp-automation
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server endpoint (
https://rube.app/mcp) to access the WhatsApp tools. - [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) due to its core function of processing external data.
- Ingestion points: Incoming WhatsApp messages received via the platform and processed during reply or management workflows.
- Boundary markers: None; the skill instructions do not specify the use of delimiters or 'ignore' instructions for the agent when handling incoming message content.
- Capability inventory: The skill possesses extensive capabilities including
WHATSAPP_SEND_MESSAGE,WHATSAPP_SEND_MEDIA,WHATSAPP_UPLOAD_MEDIA, andWHATSAPP_CREATE_MESSAGE_TEMPLATE. - Sanitization: No evidence of sanitization, filtering, or validation of incoming message content is provided in the skill documentation.
Audit Metadata