The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI tool (@membranehq/cli) globally via npm. This is a legitimate tool provided by the vendor (membranedev) to interact with their platform services.
[COMMAND_EXECUTION]: The skill relies on shell command execution via the membrane CLI to perform tasks such as platform login, connection management, and action execution.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing content from external sources.
Ingestion points: Data from the Looker platform and Membrane actions is brought into the context through the membrane action list and membrane action run commands.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between system instructions and external data ingested from these commands.
Capability inventory: The agent has capabilities to install software via npm and execute platform-specific commands using the membrane CLI tool.
Sanitization: The instructions do not describe any sanitization, filtering, or validation steps for the content returned by the external API calls.

looker