The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to perform authentication, connection management, and data retrieval tasks. These commands are part of the intended integration workflow for the Membrane platform.
[EXTERNAL_DOWNLOADS]: The skill guides the user to install the @membranehq/cli package from the NPM registry. This is the official tool provided by the vendor (membranedev) for interacting with their services.
[PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface where user-provided intents and descriptions are interpolated into CLI command arguments.
Ingestion points: User-supplied queries and descriptions are used in the membrane action list --intent "QUERY" and membrane action create "DESCRIPTION" commands (SKILL.md).
Boundary markers: No explicit boundary markers or delimiters are used in the provided command examples to isolate user input.
Capability inventory: The membrane CLI tool has the capability to perform network operations, manage credentials, and execute logic on the Membrane platform.
Sanitization: Input sanitization and validation are handled by the Membrane CLI and platform at the time of execution.

maxmind-geoip2