deep-research
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a UI automation workflow for Google Gemini, a well-known service. It creates a tab, selects a mode, and interacts with the chat interface via an MQTT-to-Browser bridge.\n- [SAFE]: All operations are performed using local tools (Bun runtime, mosquitto_pub, and mosquitto_sub). No external downloads or remote code execution patterns were identified.\n- [SAFE]: The script handles user input by incorporating it into a JSON payload for MQTT transmission, which prevents local command injection.
Audit Metadata