The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Recommends the global installation of the @membranehq/cli package from the npm registry to enable interaction with the Membrane platform.
[COMMAND_EXECUTION]: Utilizes the membrane command-line tool to perform various operations, including authentication, connection management, and running workspace actions.
[DYNAMIC_EXECUTION]: Features a membrane action create capability which allows for the dynamic generation of new actions on the Membrane platform based on natural language descriptions provided by the user.
[DATA_EXFILTRATION]: Accesses and manages records within Workiom workspaces. This data flow is central to the skill's purpose and is managed through authenticated connections to the vendor's infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Workiom records which may contain untrusted content.
Ingestion points: Data retrieved via membrane action run and search results (SKILL.md).
Boundary markers: None specified in the instructions.
Capability inventory: File system access via CLI, network operations through the platform, and action creation capabilities.
Sanitization: Instructions do not explicitly define sanitization or validation steps for ingested data.

workiom