x-twitter-monitor

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

• Third-party content exposure detected (high risk: 0.75). The required workflow for “Get the events” can ingest outsider-authored free text via webhook deliveries (an HTTP request body containing source/data and other fields) that the agent must verify and process into LLM context, creating an indirect prompt-injection path.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly describes a prepaid, billable resource ("A monitor is prepaid by the hour"), an API endpoint that creates that paid resource (POST /api/tools/x_monitor with "hours"), and states payment is done "Pay on Base (x402) or Tempo (MPP)" and that actions are "wallet-signed" and require a recoverable owner wallet. These details indicate the skill is designed to trigger/require crypto wallet payments and signed transactions to purchase/extend monitors — i.e., direct financial execution capability.