The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the NPM registry. This is the official command-line interface provided by the skill's author to facilitate platform interactions.
[COMMAND_EXECUTION]: Shell commands are used via the membrane CLI to authenticate, create connections, and run actions. These operations are standard for the intended functionality of the skill.
[DATA_EXFILTRATION]: The skill demonstrates good security posture by explicitly instructing the agent to never ask the user for API keys or tokens, instead delegating credential management to the Membrane platform.
[PROMPT_INJECTION]: While the skill ingests data from Updown.io which could technically contain malicious content, the static instructions do not contain any patterns of prompt injection or behavior overrides.

updownio