The Agent Skills Directory

[SAFE]: The skill logic is limited to reading local project files (e.g., spec.md, plan.md) and generating markdown-formatted checklists within the local feature directory.
[SAFE]: No external network requests, remote code execution, or credential access patterns were detected. It does not use any third-party scripts or unverified dependencies.
[SAFE]: The instructions include a security-conscious rule for the agent to use proper shell-style escaping for user-provided arguments, which helps prevent command injection if those arguments are passed to other tools.

bb-checklist