The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the NPM registry, which is the official tool for interacting with the Membrane platform.
[COMMAND_EXECUTION]: Shell commands are used via the membrane CLI to perform service-related tasks such as connecting to accounts and running actions. These operations are limited to the skill's documented functionality.
[PROMPT_INJECTION]: The skill interacts with external survey data via the Survser API, creating an ingestion surface for untrusted content. This is a common property of API integrations and is handled through standard CLI output.
Ingestion points: Data returned from membrane action run and membrane request as documented in SKILL.md.
Boundary markers: None specified.
Capability inventory: Execution of the membrane CLI for network and service interaction.
Sanitization: Not specified; the skill relies on the agent's default processing of command results.

survser