The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official NPM registry. This is a legitimate tool provided by the vendor 'membranedev' to manage the integration lifecycle.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to execute actions, manage connections, and handle authentication. These commands are restricted to the functionality provided by the vendor's toolset.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface where user-provided intents and descriptions are interpolated into CLI commands.
Ingestion points: User-provided strings enter the system via the --intent and --description arguments in SKILL.md.
Boundary markers: No explicit delimiters or boundary markers are present to wrap these inputs.
Capability inventory: The skill is capable of executing shell commands via the membrane CLI and performing network requests through the platform.
Sanitization: No local sanitization is performed on the user-provided strings before they are passed to the CLI.

clickfunnels-classic