The Agent Skills Directory

[SAFE]: The skill functions exclusively as a descriptive reference for a security protocol vocabulary. It contains no executable scripts or commands.
[SAFE]: Proactive security guidance is provided throughout the document, including explicit warnings against using insecure or overly permissive policies like AuthzAllowAll and non-relational storage patterns like AuthzMemberList.
[SAFE]: No patterns associated with prompt injection, data exfiltration, or obfuscation were found in the instructions or metadata.
[SAFE]: The mentioned dependency (@constructive-io/sdk) is a legitimate resource belonging to the skill's author and is cited for compatibility purposes rather than runtime installation.

constructive-safegres