The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses the npm registry to install the @membranehq/cli package, which is an official tool provided by the vendor for managing integrations.
[COMMAND_EXECUTION]: The skill relies on shell commands executed via the membrane CLI to perform tasks such as user authentication (membrane login), connecting services (membrane connect), and running automation actions (membrane action run).
[DATA_EXFILTRATION]: The skill requires network access to communicate with the WhatConverts API and the Membrane platform to manage leads and analytics data as part of its primary functionality.
[SAFE]: The skill presents an indirect prompt injection surface by ingesting user-provided intent strings to discover or create actions. However, this is part of the intended automation workflow and is processed by the vendor's platform.
Ingestion points: SKILL.md (natural language intent used in action listing and creation).
Boundary markers: Absent.
Capability inventory: Subprocess execution of the membrane CLI for action management.
Sanitization: Handled by the Membrane CLI and platform infrastructure.

whatconverts