The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official NPM registry. This is the legitimate tool for interacting with the Membrane platform as described in the skill's purpose.
[COMMAND_EXECUTION]: The skill uses the membrane command-line tool to perform actions such as login, connect, and action run. These commands are scoped to the integration's intended functionality and do not involve unauthorized system access.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes data retrieved from Userflow via action results. While instructions could theoretically be embedded in the external data, the skill is subject to standard AI guardrails.
Ingestion points: Data returned from membrane action run commands.
Boundary markers: None specified in the instructions.
Capability inventory: Shell execution via the membrane CLI tool.
Sanitization: The skill relies on the Membrane platform's internal handling of API data.

userflow