The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the npm registry. This is the official command-line interface provided by the vendor (Membrane) to manage integrations.
[COMMAND_EXECUTION]: The skill utilizes shell commands through the membrane CLI to perform authentication, connect to Cradl AI, and execute actions. These operations are restricted to the functionality provided by the vendor's tool.
[PROMPT_INJECTION]: The skill processes external data retrieved from Cradl AI (such as document analysis and customer feedback). This creates a surface for indirect prompt injection where data from the external service could potentially contain instructions intended to influence the agent's behavior. This is an inherent risk of data-processing integrations and is handled by standard agent guardrails.

cradl-ai