The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from npm. This is the official command-line interface for the Membrane platform described in the skill documentation.
[COMMAND_EXECUTION]: The instructions utilize shell commands (e.g., membrane login, membrane action run) to manage resources and interact with the DailyBot API through the Membrane provider.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it ingests untrusted data from an external source.
Ingestion points: Data enters the agent context through actions such as list-users, list-check-ins, and get-check-in-responses defined in SKILL.md.
Boundary markers: None identified in the provided instructions.
Capability inventory: The skill can perform state-changing operations like create-check-in, update-user, and send-message via membrane action run as described in SKILL.md.
Sanitization: There are no explicit instructions for the agent to sanitize or validate the content retrieved from DailyBot before processing it.

dailybot