The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command /bin/rmbc-workspace active "<user's answer>" using unsanitized free-form text input from the user. This creates a high risk of command injection if the user provides input containing shell metacharacters like semicolons, backticks, or pipes.
[COMMAND_EXECUTION]: The 'Preamble' section contains a series of bash commands designed to be executed when the skill is loaded. These commands perform environment discovery, read local configuration files, and modify the local filesystem (e.g., mkdir, touch, sed).
[DATA_EXFILTRATION]: The skill includes an analytics script bin/rmbc-analytics that logs skill usage, product names, and tier information. While an opt-in prompt is provided, the preamble logic executes this script by default if the configuration file indicates analytics are enabled.
[EXTERNAL_DOWNLOADS]: The skill implements an update mechanism via bin/rmbc-update-check which checks for newer versions of the skill suite. This involves remote connectivity to check for availability and instructions for the user to perform an 'Inline upgrade flow'.

mechanism-ideation