The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane command-line utility to perform operations such as searching for actions, creating new integrations, and running CMS workflows.\n- [EXTERNAL_DOWNLOADS]: It instructs the user to install the @membranehq/cli package globally from the NPM registry. This is a legitimate tool provided by the skill's author to manage the integration.\n- [SAFE]: The skill implements secure credential handling by using a 'connection' model where the Membrane platform manages authentication, ensuring no secrets are handled directly by the agent or stored in the skill configuration.\n- [PROMPT_INJECTION]: The skill processes content from the Scrivito CMS, which introduces a surface for indirect prompt injection.\n
Ingestion points: External data from Scrivito enters the agent context through CLI command outputs (e.g., membrane action run).\n
Boundary markers: There are no explicit delimiters or instructions for the agent to ignore instructions embedded in the retrieved content.\n
Capability inventory: The skill enables shell command execution via the membrane CLI tool.\n
Sanitization: There are no specific instructions for sanitizing or validating retrieved content before it is processed by the agent.

scrivito