whatsapp-support

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the composio CLI in a Bash environment to perform actions like searching for tools and executing commands to list, fetch, and reply to WhatsApp messages via Wati or Whautomate.
  • [PROMPT_INJECTION]: The skill processes external customer messages, which constitutes a surface for indirect prompt injection.
  • Ingestion points: Customer message history is retrieved in Step 3 using the composio execute <GET_HISTORY_SLUG> command.
  • Boundary markers: No explicit delimiters or boundary markers are used when the agent processes the retrieved message history.
  • Capability inventory: The agent has the capability to send outgoing WhatsApp messages via composio execute <SEND_REPLY_SLUG>.
  • Sanitization: No explicit sanitization or filtering of customer input is defined, though the requirement for user confirmation before sending any replies acts as a primary security control.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 08:14 PM
Security Audit — agent-trust-hub — whatsapp-support