crezco

Warn

Audited by Snyk on Apr 30, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.70). The skill instructs runtime use of the Membrane CLI via commands like "npm install -g @membranehq/cli@latest" and "npx @membranehq/cli@latest …", which fetch and execute remote code from the npm package (e.g., https://www.npmjs.com/package/@membranehq/cli) and is a required dependency for the skill to operate.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill is an integration with Crezco, a B2B payments platform, and explicitly exposes payment-related concepts (Payment Request, Payment Account, Counterparty). It instructs the agent to create/connect a Crezco connection and to discover and run Membrane actions (membrane action run ...) against that connection. Those actions can be payment operations (invoice payments, payment requests, reconciliation) — i.e., explicitly designed to move money via a payment gateway. This is not a generic tool: it is a specific payments API integration with authentication and action execution capable of initiating financial transactions.

Issues (2)

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 30, 2026, 07:37 PM
Issues
2