The Agent Skills Directory

[UNVERIFIABLE_DEPENDENCIES]: The skill instructs users to install the @membranehq/cli package globally via npm (npm install -g @membranehq/cli@latest). This is a vendor-owned resource for the Membrane platform.
[COMMAND_EXECUTION]: Multiple shell commands are utilized to manage the lifecycle of the integration, including membrane login, membrane connect, and membrane action run. These commands facilitate authentication and data interaction with the Privy service.
[DYNAMIC_EXECUTION]: The skill uses membrane action create to generate new integration logic based on a natural language description provided at runtime. This allows for dynamic functionality generation within the Membrane environment.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data.
Ingestion points: Data from the user or the Privy platform is passed into CLI arguments via the --intent, --description, and --input flags in SKILL.md.
Boundary markers: No delimiters or protective instructions are used to wrap external content in the provided command examples.
Capability inventory: The skill has the capability to execute shell commands and create new executable actions based on these inputs.
Sanitization: There is no documentation of input sanitization or validation before interpolation into command-line arguments.

privy