verifier-web

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read and re-use secret values verbatim (OTP codes from logs and Stripe API/webhook secrets written/read from files/CLI) and to type or persist them, which requires the LLM to handle and emit secret values directly.

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

• Direct money access detected (high risk: 1.00). This skill explicitly provisions and drives a Stripe payment flow: it instructs installing/configuring Stripe test keys, running the Stripe CLI/webhook listener, provides secret names (POLAR_STRIPE_SECRET_KEY, webhook secret), details how to open a checkout redirect using the checkout client_secret, and automates filling card data and clicking "Subscribe/Pay" (including test card numbers). Those are specific payment-gateway actions (create/complete charges) — i.e., direct financial execution capability.