The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the official @membranehq/cli package via npm to manage interactions with the Winston AI service. This is a standard dependency for the Membrane platform.
[COMMAND_EXECUTION]: The skill relies on the execution of shell commands through the Membrane CLI (e.g., membrane connection ensure, membrane action run) to perform its primary functions.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from Winston AI reports and API responses. While this presents a potential surface for indirect prompt injection, it is the intended functionality of the skill to retrieve and analyze this content.
Ingestion points: Data enters the context via membrane action run and membrane request commands.
Boundary markers: Not explicitly defined within the skill instructions; the agent relies on its own output handling.
Capability inventory: Command execution via membrane CLI and network requests through the Membrane proxy.
Sanitization: Relies on Membrane's server-side handling and the agent's internal safety guardrails.

winston-ai