tw-edu-meeting-facilitator
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
scripts/generate_meeting.py) to generate Word documents. This is the primary function of the skill and is implemented using standard libraries with no signs of malicious command injection.\n- [SAFE]: The skill integrates with external Google services using the official Model Context Protocol (MCP). Key operations, such as sending emails via Gmail, are explicitly restricted to draft creation, ensuring that no communications are sent without user oversight.\n- [SAFE]: No prompt injection, data exfiltration to unauthorized domains, or obfuscation techniques were identified. The skill correctly utilizes file-writing permissions within its designated scope.
Audit Metadata