The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally from the npm registry. This is the official command-line interface for the Membrane platform, which is the vendor for this skill.
[COMMAND_EXECUTION]: The instructions utilize the membrane CLI for platform operations, including authentication (membrane login), connection management (membrane connect), and executing specific integration actions (membrane action run). These are standard operations for interacting with the Membrane ecosystem.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing data retrieved from the external Reviews.io platform.
Ingestion points: Untrusted data from Reviews.io enters the agent context through the output of the membrane action run command.
Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the data received from the external API.
Capability inventory: The agent has the capability to execute shell commands via the membrane CLI for managing platform state and executing actions.
Sanitization: No specific sanitization or validation logic is defined for the external data before it is processed by the agent.

reviewsio