The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data from external Lexoffice API responses which could contain malicious instructions.
Ingestion points: Data retrieved through actions such as list-invoices, get-contact, or direct proxy requests.
Boundary markers: Absent; there are no instructions to the agent to treat external content as untrusted or to wrap it in specific delimiters.
Capability inventory: The skill utilizes the membrane CLI to execute actions and make network requests.
Sanitization: No sanitization or validation steps are defined for the data returned from the API.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli tool from the NPM registry.
[COMMAND_EXECUTION]: The skill heavily relies on executing the membrane command-line utility to manage connections, search for actions, and run API requests.

lexoffice