The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli Node.js package. This is an official tool provided by the vendor to facilitate secure communication with the service.
[COMMAND_EXECUTION]: The instructions utilize the membrane CLI for various operations, including authentication (membrane login), connection management (membrane connect), and executing API actions (membrane action run). These commands are standard for this platform's workflow.
[PROMPT_INJECTION]: The skill processes external data from Ghost Inspector, which represents a potential surface for indirect prompt injection.
Ingestion points: API responses from Ghost Inspector retrieved via membrane action run or membrane request (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or guardrails for processing the retrieved data.
Capability inventory: The agent has the ability to execute shell commands using the membrane CLI to retrieve or modify remote resources.
Sanitization: There are no explicit instructions for sanitizing or validating the data returned from the external service before processing.

ghost-inspector