whatsapp-cloud-api

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides a set of well-documented boilerplate templates and utility scripts for Meta's official WhatsApp Business Cloud API. It correctly implements security protocols such as timing-safe HMAC validation for webhooks and provides guidance on secure token management.\n- [PROMPT_INJECTION]: The skill processes untrusted external data (WhatsApp messages) which constitutes an indirect prompt injection surface if the content is forwarded to an LLM.\n
  • Ingestion points: Incoming messages are received via POST requests to the /webhook endpoint in assets/boilerplate/python/app.py and assets/boilerplate/nodejs/src/index.ts.\n
  • Boundary markers: No specific boundary markers or 'ignore' instructions are present in the provided templates to isolate untrusted user input.\n
  • Capability inventory: The skill possesses capabilities to send messages and interact with the WhatsApp API, which could be misused if an attacker successfully injects instructions into the processing pipeline.\n
  • Sanitization: The boilerplate code provides basic extraction but lacks sanitization or validation of the message body before it is processed by the logic handlers.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 07:35 PM