create-payment-credential

Fail

Audited by Snyk on May 8, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill explicitly requires retrieving raw payment credentials (card PAN/CVC and one-time SPTs) and passing raw WWW-Authenticate headers into CLI commands (e.g., --challenge '' and printing/filling card details), which forces the agent to handle and potentially output secret values verbatim—an exfiltration risk despite recommendations to mask or write to a file.

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

  • Third-party content exposure detected (high risk: 1.00). The skill's Core flow Step 2 explicitly instructs the agent to "Navigate to the merchant page — browse it, read the page content" and to probe merchant URLs and parse WWW-Authenticate headers via the mpp pay flow, meaning the agent will fetch and interpret arbitrary public merchant web content that directly determines credential type and subsequent payment actions.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires running "npx @stripe/link-cli" (which fetches and executes remote package code from the npm registry, e.g. https://registry.npmjs.org/@stripe/link-cli or via npx @stripe/link-cli@latest) at runtime, so it executes remote code and is a required dependency.

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

  • Direct money access detected (high risk: 1.00). The skill explicitly provides tools and step-by-step commands to create and use payment credentials (virtual card PANs and Shared Payment Tokens) via Link/Stripe. It includes commands to authenticate, create spend requests, retrieve card numbers (number, cvc, exp), and perform programmatic payments (mpp pay) — i.e., obtaining and using credentials to execute real purchases. This is a specific payment integration (Stripe/Link) and therefore grants direct financial execution authority.

Issues (4)

W007
HIGH

Insecure credential handling detected in skill instructions.

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
HIGH
Analyzed
May 8, 2026, 05:37 PM
Issues
4