The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill guides the user to install the @membranehq/cli package from the NPM registry and also uses npx to run commands. These resources originate from the vendor and are necessary for the skill's intended operation.\n- [COMMAND_EXECUTION]: Multiple shell commands using the membrane CLI are documented, including login, connect, and action run. These commands are standard for the Membrane platform and are used to manage connections and execute actions within the authorized environment.\n- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes data from external Reflect notes.\n
Ingestion points: Note content and titles are retrieved from Reflect via the membrane action run command.\n
Boundary markers: There are no specific instructions or delimiters provided to the agent to distinguish between instructions and data retrieved from notes.\n
Capability inventory: The agent has the ability to run existing actions and create new actions (membrane action create), which could involve network or data operations.\n
Sanitization: No explicit sanitization or validation of the note content is described before the data is processed by the agent.

reflect