The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from the official NPM registry to provide the necessary command-line tools for interacting with the Membrane platform.
[COMMAND_EXECUTION]: Executes shell commands via the membrane CLI to perform authentication, create connections to PhoneBurner, and run API actions.
[PROMPT_INJECTION]: The skill uses natural language intents as parameters for CLI commands, which represents a surface for indirect prompt injection if the inputs are derived from untrusted sources.
Ingestion points: Untrusted data may enter the agent context through the --intent parameter in the membrane action list command and the DESCRIPTION parameter in membrane action create (SKILL.md).
Boundary markers: None present; parameters are interpolated directly into shell command templates.
Capability inventory: The skill allows searching for, creating, and executing arbitrary API actions via membrane action run and membrane action create (SKILL.md).
Sanitization: No specific sanitization or validation of the input query strings is described in the skill instructions.

phoneburner