The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the NPM registry. This tool is provided by the vendor to facilitate communication with the Membrane platform.
[COMMAND_EXECUTION]: The instructions guide the agent to perform multiple shell commands using the membrane CLI, including login, connect, and action run. These are core to the skill's intended operation.
[PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection because it ingests data from external Leyr actions and creates new actions based on natural language descriptions provided to the CLI.
Ingestion points: Data retrieved through membrane action list and the output of membrane action run in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore nested commands are defined in the provided agent instructions.
Capability inventory: The skill can execute shell commands, perform authenticated network operations via the platform, and dynamically generate and run new actions.
Sanitization: The instructions do not specify any validation or sanitization protocols for data ingested from the Leyr platform before it is used by the agent.

leyr