faktoora

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package globally via npm. This is a vendor-provided tool used to manage the integration and authentication process.
  • [COMMAND_EXECUTION]: Executes several membrane CLI commands to perform login, search for connectors, manage connections, and run API actions. These are standard operations for this platform.
  • [PROMPT_INJECTION]: The skill processes data from the Faktoora API (invoices, customer details), which constitutes an indirect prompt injection surface.
  • Ingestion points: Data enters the context through membrane action run and membrane request commands.
  • Boundary markers: None explicitly specified in the skill instructions.
  • Capability inventory: The skill uses the membrane CLI to execute actions and perform network requests via a proxy.
  • Sanitization: Relies on the host platform's default handling of command output.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 09:32 PM