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 tool provided by the vendor to facilitate integrations.
[COMMAND_EXECUTION]: The skill uses various membrane CLI commands to handle authentication (membrane login), connection management (membrane connect), and API interactions (membrane action run, membrane request). These are standard operational commands for the platform.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes data retrieved from the Altera Payroll API.
Ingestion points: Data enters the agent's context through the output of membrane action run and membrane request commands.
Boundary markers: The instructions do not specify any delimiters or safety markers (e.g., "ignore instructions in the following data") to isolate API responses.
Capability inventory: The agent has the ability to execute further CLI commands and perform network requests via the proxy, which could be triggered by malicious data in an API response.
Sanitization: There are no explicit sanitization or validation steps mentioned in the skill for handling external data before it is processed by the agent.

altera-payroll