mqtt

Warn

Audited by Snyk on Mar 7, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to subscribe to MQTT topics (e.g., the "Subscribe to device commands" example using client.subscribe('commands/device1') and client.on_message) and to connect to brokers like HiveMQ/Mosquitto, meaning it will ingest untrusted, user-generated messages from third-party brokers that can contain commands influencing behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 05:46 PM