The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package from the official npm registry. This is a standard dependency for the skill's functionality and originates from the vendor's official package scope. \n- [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform authentication, search for connectors, and execute actions. These commands are the primary and intended method of interaction for this platform integration. \n- [PROMPT_INJECTION]: The skill ingests untrusted data from the Cubicl API (via membrane action list and membrane request) which the agent then uses to determine action schemas. While this is a surface for indirect prompt injection, it is the standard operational mode for this type of integration and no malicious intent was found. \n
Ingestion points: SKILL.md instructions for parsing membrane action list and membrane request output. \n
Boundary markers: Absent. \n
Capability inventory: Shell command execution via the membrane CLI. \n
Sanitization: Absent.

cubicl