The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Membrane CLI (membrane) to perform authorized actions and management tasks. These commands are restricted to the vendor's own platform ecosystem.
[EXTERNAL_DOWNLOADS]: Recommends the installation of the official @membranehq/cli package. This is a legitimate vendor resource used to facilitate the intended integration logic.
[DATA_EXFILTRATION]: Network operations are performed through the membrane request proxy, which handles authentication server-side. There is no evidence of unauthorized data transfer or sensitive file access.
[CREDENTIALS_UNSAFE]: The skill explicitly instructs users to let the platform handle credentials rather than providing API keys or tokens to the agent, which is a significant security positive.

browserless