xero

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the global NPM registry. This is a verified vendor package required for the skill to communicate with the Membrane platform.
  • [COMMAND_EXECUTION]: The skill utilizes several CLI commands (membrane login, membrane connect, membrane action run) to manage the Xero lifecycle. These commands are scoped to the Membrane environment and are used to execute pre-defined actions.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it reads data (e.g., invoices, contacts) from an external service (Xero).
  • Ingestion points: External accounting data enters the agent context via the output of membrane action run commands.
  • Boundary markers: Absent; data is returned as JSON and processed directly by the agent.
  • Capability inventory: The skill can execute file-system commands via the CLI, modify records in Xero, and create new actions on the Membrane platform.
  • Sanitization: No explicit sanitization or filtering of the Xero data is performed within the skill instructions.
  • [SAFE]: The skill follows security best practices by delegating authentication to a specialized platform (Membrane) rather than requesting or storing raw credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 08:33 AM