The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the public npm registry. This is the official command-line tool for the Membrane platform.
[COMMAND_EXECUTION]: The instructions involve executing various membrane CLI commands to manage authentication (membrane login), connection setup (membrane connect), and action execution (membrane action run). These are standard operational procedures for the vendor's toolset.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by interpolating user-provided intents and parameters into CLI commands.
Ingestion points: Untrusted data enters via the --intent argument in membrane action list and the --input argument in membrane action run as described in SKILL.md.
Boundary markers: No explicit delimiters or warnings are present to instruct the agent to ignore instructions embedded in the user-provided data.
Capability inventory: The skill utilizes the membrane CLI to interact with external APIs, create new actions, and execute code on the Membrane platform.
Sanitization: No explicit sanitization or validation logic is defined for the input parameters or search queries.

syniverse