whatsapp-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates processing and replying to incoming WhatsApp messages, which are untrusted external data sources. This creates a potential surface for indirect prompt injection where an attacker could send a message containing hidden instructions to influence the agent's behavior.
- Ingestion points: Incoming message content processed via the WhatsApp communication tools (e.g.,
WHATSAPP_SEND_REPLY). - Boundary markers: The skill does not provide specific instructions for using delimiters or boundary markers to isolate untrusted message text from the agent's instructions.
- Capability inventory: The skill possesses significant capabilities including sending text/media messages, managing business profiles, and creating message templates.
- Sanitization: There is no mention of sanitization or filtering protocols for incoming message data before it is processed by the AI agent.
Audit Metadata