The Agent Skills Directory

[SAFE]: The skill serves as a security defensive mechanism. It provides instructions to the agent to avoid asking for secrets in chat and to never hardcode them in files.
[SAFE]: It promotes standard security hygiene, such as correctly configuring .gitignore for .env files and setting appropriate file permissions (chmod 600).
[SAFE]: The skill references well-known and trusted services such as Supabase, Vercel, OpenAI, and GitHub for managing secrets through their official CLI tools and dashboard interfaces.
[SAFE]: No obfuscation, data exfiltration patterns, or unauthorized command execution were detected. The skill is purely instructional and aimed at improving the security posture of projects using the M·MAKE stack.

secrets-policy