zenf-mcp
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local binary located at
apps/daemon/bin/zenfdto perform configuration audits and setup tasks. - Evidence:
apps/daemon/bin/zenfd mcp check --client agy --jsonandapps/daemon/bin/zenfd mcp setup --client agy. - Context: These commands are part of the core functionality to integrate the Model Context Protocol (MCP) server and are only executed after verifying the state or receiving user consent.
- [SAFE]: The skill implements a strict "Human-in-the-loop" policy for all modification actions.
- Evidence: 'Strictly forbid running setup commands or overwriting user configuration files automatically' and 'HALT TURN IMMEDIATELY TO AWAIT USER RESPONSE'.
- Context: This follows security best practices for AI agents by ensuring the user reviews the exact command and JSON configuration before it is applied to the system.
Audit Metadata