Skills
skills/membranedev/application-skills/livechat/Gen Agent Trust Hub

livechat

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the official Membrane CLI (@membranehq/cli) globally from the npm registry. This package is the primary tool used by the skill and originates from the skill's verified vendor.
  • [COMMAND_EXECUTION]: Various shell commands are used to interact with the membrane CLI, including membrane login, membrane connect, and membrane action run. These operations are used as intended to manage LiveChat connections and execute specific integration logic.
  • [DATA_EXFILTRATION]: No sensitive data exposure patterns were detected. The skill specifically instructs the agent to let Membrane manage credentials server-side and explicitly warns against asking the user for API keys or tokens locally.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:53 PM
Security Audit — agent-trust-hub — livechat