install-mcp
Warn
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform file system operations (read and write) on sensitive configuration files belonging to third-party applications.
- [COMMAND_EXECUTION]: Targeted files include
~/.claude.json,~/Library/Application Support/Claude/claude_desktop_config.json, and~/.cursor/mcp.json. These files typically contain environment variables, user settings, and potentially authentication credentials for the respective AI platforms.
Audit Metadata