The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to install the @membranehq/cli package globally from the npm registry, which is the official tool provided by the vendor.
[COMMAND_EXECUTION]: The skill uses several membrane CLI commands for logging in, connecting to Appcircle, and executing actions. These commands represent the primary interface for managing integrations within the platform.
[REMOTE_CODE_EXECUTION]: The skill instructs the use of npx to run the @membranehq/cli directly. This is a standard way to execute vendor-provided tooling and does not involve untrusted remote sources.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection due to its interaction with external Appcircle data. \n
Ingestion points: Untrusted data enters the agent context via the output of membrane action run and membrane action list commands. \n
Boundary markers: No specific delimiters or boundary warnings are provided in the instructions to distinguish external data from agent instructions. \n
Capability inventory: The skill allows for command execution, action creation, and connection management through the membrane CLI. \n
Sanitization: The instructions do not specify any sanitization, validation, or filtering of the content retrieved from Appcircle.

appcircle