The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane CLI to interact with the Digiteal platform, which is the intended and standard method for this integration. Use of membrane action run and membrane request facilitates API interaction via a managed proxy.
[EXTERNAL_DOWNLOADS]: The skill requires installing the @membranehq/cli package from the NPM registry, which is an official tool provided by the vendor.
[PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection by processing external data from Digiteal API responses.
Ingestion points: API response data retrieved via membrane action run and membrane request commands in SKILL.md.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the processed external content.
Capability inventory: The skill can execute actions to manage documents, templates, and users via the Membrane CLI.
Sanitization: No explicit data validation or sanitization of the API response data is implemented in the instruction set.
[SAFE]: The skill follows security best practices for credential management by utilizing Membrane's server-side authentication system, ensuring that API keys and tokens are not handled directly by the agent or stored locally.

digiteal