whatsapp-alt

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This skill explicitly enables bypassing Meta's official WhatsApp Business controls by linking numbers via QR and routing traffic through managed residential proxies or user Android devices, a design that intentionally facilitates origin-masking and evasion of platform safeguards and thus materially increases the risk of abuse (spam, impersonation, large-scale unsolicited messaging).

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required workflow includes receiving inbound message.inbound / message.status webhook payloads that contain outsider-authored free text (e.g., data.text from WhatsApp contacts) which can be forwarded into the agent’s LLM context by the runtime handler.