The Agent Skills Directory

[SAFE]: The skill uses official vendor-owned tools and domains including the @membranehq/cli NPM package and the getmembrane.com domain. These are legitimate resources associated with the skill's author context.
[SAFE]: Authentication is handled through a secure browser-based login flow (membrane login) and connection management system, preventing the need for the agent to handle or store raw credentials locally.
[SAFE]: No malicious patterns such as prompt injection, data exfiltration to unknown domains, or unauthorized privilege escalation were detected in the instructions or command examples.

docker-hub