setup-adyen

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill contains only instructional markdown files and configuration metadata. There are no executable scripts (Python, JavaScript, shell) or binary files provided with the skill.
  • [SAFE]: All external references, documentation URLs, and package names point to official Adyen domains (adyen.com, adyenpayments.com) or official GitHub repositories (github.com/Adyen). This aligns with recognized safe services.
  • [SAFE]: The skill enforces critical security protocols for payment processing, including mandatory HMAC verification for incoming webhooks using constant-time comparison and server-side authentication for API requests.
  • [SAFE]: No hardcoded production credentials were found. Test data, such as sandbox card numbers and passwords, are clearly labeled for use only in Adyen's test environment and are sourced from official public documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines workflows for processing untrusted external data from payment results and webhooks. It explicitly mitigates risk by instructing the agent to verify cryptographic signatures (HMAC), validate environment markers (live vs. test), and cross-check transaction integrity (amount, currency, and reference) before performing any business logic or fulfillment.
  • Ingestion points: Webhook payloads described in references/adyen-webhooks.md and redirect results in references/adyen-checkout.md.
  • Boundary markers: Explicit instructions to use HMAC verification and ignore embedded instructions in data.
  • Capability inventory: API calls for payment creation, capture, and refund as detailed in references/adyen-modifications.md.
  • Sanitization: Use of constant-time comparison for signatures and integer-based amount validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 05:13 AM