stripe-reconcile

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to set environment variables and run CLI commands that embed the Stripe webhook secret value verbatim (e.g., npx convex env set ... "whsec_..."/printf 'whsec_...'), which requires the LLM to handle and output secret values directly, creating exfiltration risk.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly centered on Stripe (a payment gateway). It includes Stripe-specific commands and configuration (e.g., stripe CLI: stripe webhook_endpoints update <id> --url ..., setting STRIPE_WEBHOOK_SECRET env var, and code examples that set subscription_data.trial_end / checkout session behavior). Those are concrete, payment-gateway operations and configuration changes that directly affect payment processing and webhook handling. This meets the criterion for direct financial execution authority.