The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli npm package. This is the official command-line interface provided by the vendor (membranedev) to interact with their platform services.
[COMMAND_EXECUTION]: All platform operations, such as listing projects, managing deployments, and executing actions, are performed using the membrane CLI tool. This provides a structured and controlled environment for executing operations.
[DATA_EXFILTRATION]: The skill communicates with the DeployHQ API through a proxy managed by the vendor. This communication is required for the skill's primary function and uses a secure mechanism to inject authentication headers automatically.
[PROMPT_INJECTION]: The skill processes data from DeployHQ API responses, representing a surface for potential indirect prompt injection if the external data contains instructions for the agent.
Ingestion points: API response content from DeployHQ retrieved via CLI actions and proxy requests.
Boundary markers: The instructions do not define specific delimiters or warnings to isolate API data from the agent's control flow.
Capability inventory: The skill can execute pre-defined actions and make arbitrary API requests through the membrane CLI.
Sanitization: No specific sanitization or validation logic is defined for the data returned from the external API.

deployhq