NYC

iot-developer

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill connects to a public MQTT broker (e.g., ws://broker.hivemq.com:8000/mqtt and mqtt_server = "broker.hivemq.com") and subscribes to topics like "home/temperature" and "home/humidity", meaning it ingests untrusted, user-published messages from the open internet that the agent reads and acts on.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:25 PM