The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package from the official NPM registry. This tool is provided by the vendor (membranedev) to facilitate the integration and is a standard dependency for this ecosystem.
[COMMAND_EXECUTION]: The skill instructions involve executing commands via the membrane CLI to authenticate, manage connections, and interact with the Adalo API. These actions are limited to the intended functionality of the integration and do not involve suspicious privilege escalation.
[PROMPT_INJECTION]: The skill processes external data from Adalo collections, which introduces a surface for indirect prompt injection. This is a common characteristic of data-integration skills.
Ingestion points: Data retrieved through Adalo actions like get-collection-record and list-collection-records.
Boundary markers: Not explicitly used in the provided markdown instructions.
Capability inventory: Execution of actions and network requests through the membrane command-line tool.
Sanitization: Relies on the underlying AI agent's safety guardrails to process retrieved content safely.

adalo