lusha

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli global npm package. This package is the official command-line interface for the Membrane platform.
  • [COMMAND_EXECUTION]: Executes shell commands via the membrane CLI to perform authentication (membrane login), connection setup (membrane connect), and action execution (membrane action run).
  • [CREDENTIALS_UNSAFE]: The skill adheres to security best practices by explicitly advising against asking for or storing API keys locally, delegating all credential management to the Membrane platform.
  • [PROMPT_INJECTION]: The skill ingests contact and company data from the Lusha API (ingestion points in SKILL.md: membrane action run, membrane request). This data enters the agent context and represents an indirect prompt injection surface. The skill relies on standard tool outputs (capability inventory: membrane subprocess calls) and relies on structured data usage over raw API calls to mitigate risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 06:41 PM