The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the NPM registry and utilizes npx to execute vendor-provided tools. These resources are official components of the Membrane ecosystem.
[COMMAND_EXECUTION]: The skill relies on executing membrane CLI commands to perform tasks such as authentication, listing actions, and proxying API requests. This is the intended operational model for the skill.
[PROMPT_INJECTION]: The skill interacts with the Aiia API and retrieves external data. This creates an attack surface for indirect prompt injection where malicious content in the API responses could influence agent behavior if not properly sanitized before being included in subsequent prompts.
Ingestion points: Output from membrane action run and membrane request commands.
Boundary markers: None identified in the provided instructions.
Capability inventory: Execution of membrane CLI commands via terminal/subprocess.
Sanitization: Not explicitly defined within the skill's logic.

aiia