The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package from the NPM registry. This is an official tool provided by the vendor (Membrane) to facilitate the integration.
[COMMAND_EXECUTION]: The skill relies on the membrane command-line tool to perform operations such as login, connection management, and running actions. These commands are standard for the intended integration logic.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content retrieved from the external Kontent.ai environment.
Ingestion points: Content variants, asset metadata, and action outputs retrieved from Kontent.ai via the membrane action run command.
Boundary markers: The provided instructions do not include specific delimiters or warnings to ignore instructions embedded within the retrieved data.
Capability inventory: The skill has the ability to execute shell commands via the Membrane CLI and interact with network services through the Membrane platform.
Sanitization: There is no explicit sanitization step mentioned in the skill instructions for data retrieved from the CMS.

kontentai