iot-expert

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

• Third-party content exposure detected (high risk: 0.90). The skill subscribes to and processes MQTT topic messages from external brokers (see MQTTClient._on_message and IoTPipeline.register_device subscribing to sensors/temperature/{device_id}), which are untrusted, user-generated network payloads the agent reads and interprets as part of its workflow.