shippo
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the membrane CLI tool to perform authentication, search for connectors, and execute actions. This is a core component of the vendor's integration framework.
- [EXTERNAL_DOWNLOADS]: Instructions include the global installation of the @membranehq/cli package via npm to enable the skill's functionality. This package is part of the official Membrane ecosystem.
- [DATA_EXFILTRATION]: The skill routes API requests to Shippo via a managed proxy. This design is intended to centralize authentication and securely manage API credentials on the server side.
- [PROMPT_INJECTION]: The skill ingests data from Shippo API endpoints (Ingestion Point: SKILL.md), lacks explicit boundary markers or sanitization, and has capabilities including command execution via the membrane CLI. This surface for indirect prompt injection is inherent to the integration's purpose.
Audit Metadata