The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the Membrane CLI from the public NPM registry.
Evidence: npm install -g @membranehq/cli@latest in SKILL.md.
[COMMAND_EXECUTION]: The skill performs multiple shell operations using the membrane command-line tool to manage sessions and data.
Evidence: Commands include membrane login, membrane connect, and membrane action run.
[PROMPT_INJECTION]: The skill ingests untrusted data from the MoMo platform, which creates a surface for indirect prompt injection attacks.
Ingestion points: Retrieves and processes MoMo Records using membrane action run.
Boundary markers: None identified; record content is processed directly in the agent's context.
Capability inventory: The skill has the ability to execute shell commands via the CLI and create new actions (membrane action create).
Sanitization: No validation or sanitization of the retrieved record content is specified before it is used by the agent.

momo