The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package globally via npm to enable integration logic. This is a vendor-provided tool from the skill author's organization.
[COMMAND_EXECUTION]: Utilizes the membrane CLI for operations including authentication, connector discovery, and executing API actions. These commands are necessary for the skill's primary functionality.
[SAFE]: Implements secure secret management by utilizing the Membrane platform as an authentication proxy, ensuring that API keys and tokens are never handled or stored locally by the agent.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing data retrieved from the Restack API.
Ingestion points: Data retrieved through membrane action run and membrane request commands.
Boundary markers: Absent; there are no specific markers used to delimit external data from agent instructions.
Capability inventory: The skill has the capability to execute shell commands via the membrane CLI.
Sanitization: No explicit sanitization or filtering of the API response data is implemented within the skill instructions.

restack