The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package. This is a legitimate tool provided by the vendor (membrane) for platform interaction.
[COMMAND_EXECUTION]: Uses the membrane CLI to manage connections and execute integration actions. These commands are standard for the platform's workflow and do not involve suspicious parameters.
[CREDENTIALS_UNSAFE]: The skill implements secure credential management by advising against the use of raw API keys. Instead, it uses a connection-based system where tokens are managed server-side by the Membrane platform.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes data returned from Clerk.io APIs.
Ingestion points: Data returned from membrane action run and metadata from membrane action list.
Boundary markers: None explicitly defined in the skill markdown.
Capability inventory: Can list, create, and execute actions via the Membrane CLI.
Sanitization: Relies on the underlying agent's default safety filters and platform-level handling.

clerkio