agentic-commerce-protocol

Warn

Audited by Snyk on May 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's "Capability Negotiation" flow includes a client-side checkSellerCapabilities(sellerUrl) that POSTs to an arbitrary sellerUrl/agentic-checkout/capabilities and uses the returned capabilities to decide compatibility and next actions, clearly consuming untrusted third-party responses that can influence agent behavior.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly an "Agentic Commerce Protocol" for AI-driven commerce and includes concrete payment endpoints and flows (POST /agentic-checkout/create-checkout, /confirm-checkout), handles payment_token, and references payment processors and credentials (PAYMENT_PROCESSOR_API_KEY, processor: 'stripe'). It describes payment handler types (delegate_payment, seller-backed, payment link), supported methods (card, bank_transfer), and shows confirm-checkout processing payments and producing orders. These are specific payment integrations and transaction-executing operations (Stripe referenced), not generic tooling—therefore it grants direct financial execution capability.

Issues (2)

W011
MEDIUM

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

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 17, 2026, 09:51 PM
Issues
2
Security Audit — snyk — agentic-commerce-protocol