automate-whatsapp

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of local Node.js scripts to interface with the Kapso API for managing workflows, triggers, and databases.
  • [EXTERNAL_DOWNLOADS]: Instructions include running npm i to install necessary dependencies from the official npm registry.
  • [DYNAMIC_EXECUTION]: The skill facilitates the creation and deployment of custom JavaScript 'handler' functions to the Kapso runtime, which is a core feature of the automation platform.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Workflow triggers (WhatsApp messages) and database queries provide external data that enters the agent context via scripts like query-rows.js and get-context-value.js.
  • Boundary markers: No specific delimiters or safety instructions for handling untrusted trigger data are defined in the provided documentation.
  • Capability inventory: The skill can perform network operations and execute local scripts (as seen in the scripts/ directory) to manage the automation lifecycle.
  • Sanitization: No explicit data sanitization or validation logic is documented for the processing of incoming message data or database contents within the prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 09:19 AM
Security Audit — agent-trust-hub — automate-whatsapp