The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli global package from the official NPM registry, which is the vendor's tool for interacting with their platform.
[COMMAND_EXECUTION]: The instructions utilize the membrane CLI to perform operations such as login, connection management, and action execution. These are standard operations for the platform's workflow.
[REMOTE_CODE_EXECUTION]: The skill runs hosted integration logic on the Membrane platform via the membrane action run command. This is the intended mechanism for executing API integrations.
[PROMPT_INJECTION]: The skill processes data from external Setmore records (e.g., customer names, appointment notes), creating a surface for indirect prompt injection if those records contain malicious instructions.
Ingestion points: Output from membrane action run containing Setmore data from SKILL.md.
Boundary markers: Not explicitly defined in the provided instructions.
Capability inventory: Network access and command execution via the membrane CLI.
Sanitization: Not specified; the skill relies on the agent's inherent safety guardrails when processing external content.

setmore