The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to interact with the SARE platform, performing tasks like managing campaigns, leads, and actions. This involves the installation of the @membranehq/cli package and execution of commands for authentication and resource management.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from the SARE API. \n- Ingestion points: Data returned by CLI commands such as membrane action list, membrane action run, and membrane request. \n- Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided to protect the agent context. \n- Capability inventory: The skill possesses the ability to execute actions via membrane action run and perform arbitrary network requests through the membrane request proxy. \n- Sanitization: No sanitization or validation of external marketing data is performed before the agent processes it.

sare