The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands using the Membrane CLI (membrane) to manage Vultr resources, including membrane login, membrane connect, and membrane action run.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the NPM registry to function, which is a standard dependency for the vendor's ecosystem.
[PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8) due to its ability to ingest and act upon external data.
Ingestion points: Data retrieved from the Vultr API via membrane request and metadata retrieved via membrane action list (SKILL.md).
Boundary markers: Absent; the instructions do not specify the use of delimiters or provide warnings to the agent regarding potentially malicious content in API responses.
Capability inventory: The skill can perform significant cloud infrastructure modifications (e.g., managing virtual machines, SSH keys, and firewall groups) via membrane action run and membrane request (SKILL.md).
Sanitization: Absent; there is no mention of validating or sanitizing retrieved API data before it is processed by the agent.

vultr