The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the official @membranehq/cli package from the NPM registry. This is a vendor-owned resource used for its intended purpose of platform integration.
[COMMAND_EXECUTION]: The skill uses shell commands through the membrane CLI to perform data operations, manage authentication sessions, and execute platform actions. These commands are documented and scoped to the vendor's integration logic.
[DATA_EXFILTRATION]: The skill demonstrates safe credential handling by explicitly directing the agent to use Membrane's server-side authentication flows rather than requesting API keys or sensitive tokens from the user.
[PROMPT_INJECTION]: The skill ingests data from external actions and records, creating a surface for indirect prompt injection. However, the operations are limited to the vendor's CLI environment.
Ingestion points: Output from membrane action list and membrane action run commands.
Boundary markers: Absent.
Capability inventory: Shell command execution via the membrane CLI.
Sanitization: Absent.

momo