observe-whatsapp

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Node.js scripts (e.g., messages.js, webhook-deliveries.js, whatsapp-health.js) to perform diagnostic operations and query the Kapso API.\n- [EXTERNAL_DOWNLOADS]: Standard dependency installation is performed via npm i to support the execution of the diagnostic scripts.\n- [PROMPT_INJECTION]: The skill ingests untrusted external data from WhatsApp messages and API logs, which constitutes an indirect prompt injection surface.\n
  • Ingestion points: scripts/messages.js, scripts/api-logs.js, and scripts/webhook-deliveries.js fetch external message content and log data.\n
  • Boundary markers: No specific delimiters or warnings regarding embedded instructions in external data are documented.\n
  • Capability inventory: Execution of local scripts via Node.js and interaction with the Kapso API.\n
  • Sanitization: No explicit sanitization or filtering of external message content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 02:06 PM
Security Audit — agent-trust-hub — observe-whatsapp