whatsapp-business

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle WhatsApp conversations, messages, and templates, which are external data sources that could contain malicious instructions.
  • Ingestion points: The skill reads incoming message bodies and template configurations from the WhatsApp Business API via the Maton gateway.
  • Boundary markers: The instructions lack explicit boundary markers or directions to the agent to treat incoming message content as untrusted data.
  • Capability inventory: The skill utilizes Python and JavaScript snippets to perform network requests (urllib.request, requests, fetch), write to the API, and manage OAuth connections.
  • Sanitization: No sanitization or escaping of external content is specified before the agent processes or responds to it.
  • [DATA_EXFILTRATION]: The skill requires the use of a sensitive environment variable (MATON_API_KEY) and transmits it to the maton.ai infrastructure (gateway.maton.ai, ctrl.maton.ai). These are non-whitelisted external domains.
  • [COMMAND_EXECUTION]: The documentation provides multiple examples instructing the agent to execute complex Python scripts using shell heredocs (python <<'EOF'). These scripts utilize standard libraries to perform network operations and process JSON data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 01:51 PM
Security Audit — agent-trust-hub — whatsapp-business