adyen

Warn

Audited by Snyk on Oct 13, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The skill interacts with the Adyen payment platform via the Membrane CLI, allowing an agent to manage data, records, and run actions or proxy requests where payment records or transaction data could contain external free text.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the installation and execution of the @membranehq/cli package via npm from an external registry, which lacks verified first-party provenance, constituting a medium-tier operational dependency.

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

  • Direct money access detected (medium risk: 0.30). The skill integrates with Adyen, a global payment platform, supporting direct financial operations such as payments, refunds, and billing events (SKILL.md:23-29). It uses the Membrane CLI to interact with Adyen and execute actions or make proxied API requests (SKILL.md:33, 118-138). Authentication and connection setup are handled via Membrane login and connection ensure flows (SKILL.md:45-70), establishing independent service-layer authentication for the connection.

Issues (3)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

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
Oct 13, 2026, 02:41 PM
Issues
3