The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package from the NPM registry. This is an official tool provided by the vendor for platform interaction.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform operational tasks such as logging in, connecting to services, and managing data actions.
[REMOTE_CODE_EXECUTION]: The skill employs npx to run the vendor's CLI tool directly from the official package registry for action discovery.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface related to the ingestion of external data.
Ingestion points: The agent processes output from the membrane action run and membrane action list commands which retrieve data from the external platform.
Boundary markers: No explicit delimiters or instructions are provided to distinguish between internal instructions and external data ingested at runtime.
Capability inventory: The agent has access to shell commands via the membrane CLI to interact with business identity and compliance data.
Sanitization: The skill does not describe any methods for validating or sanitizing the content returned by external actions before it is used by the agent.

middesk