The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package globally via npm. This CLI tool is a vendor-owned resource used for authentication and service management.
[COMMAND_EXECUTION]: The skill utilizes shell commands via the membrane CLI to perform core operations, including membrane login, membrane connect, and membrane action run.
[PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection through its interaction with external Astronaut data.
Ingestion points: External data regarding missions, astronauts, and vehicles is retrieved through CLI actions defined in SKILL.md and loaded into the agent's context.
Boundary markers: There are no explicit delimiters or boundary markers specified in the instructions to isolate untrusted external data from the agent's internal logic.
Capability inventory: The skill allows for command execution and network operations through the Membrane CLI infrastructure, enabling the execution of arbitrary actions.
Sanitization: The documentation does not specify any sanitization or validation routines for data retrieved from Astronaut before it is processed by the agent.

astronaut