The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's primary functionality is delivered through the execution of the membrane command-line interface (CLI). This includes logging in, connecting to services, searching for actions, and running those actions.
[EXTERNAL_DOWNLOADS]: Instructions guide the user to install the @membranehq/cli package globally via npm. This package is provided by the skill's authoring organization (Membrane) and is necessary for the skill's operation.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection. It retrieves data from an external source (the Decision Journal service) and presents it to the agent.
Ingestion points: Data is received from the output of membrane action run and membrane action list commands.
Boundary markers: The instructions do not define specific delimiters or provide "ignore embedded instructions" warnings for the agent when processing this data.
Capability inventory: The agent is empowered to execute shell commands using the membrane CLI tool based on its interpretation of tasks.
Sanitization: There is no evidence of sanitization or filtering of the retrieved content before it is processed by the agent's prompt.

decision-journal