hunt-fintech-graphql

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document is an explicit offensive playbook describing step-by-step exploits (double-spend, idempotency replay, asymmetric IDOR, mass-assignment) and payloads to move funds and access PII in fintech GraphQL systems, enabling unauthorized monetary theft and data exposure.

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

• Third-party content exposure detected (low risk: 0.10). The skill guidance describes a GraphQL money-movement hunting workflow (e.g., mapping mutations, running GraphQL queries/mutations with attacker-supplied variables like amount, idempotencyKey, and sourceAccountId) where outsider-authored free text is injected into runtime GraphQL requests rather than read passively from a monitored feed.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly about fintech money-movement GraphQL APIs and contains concrete, actionable money-moving operations (e.g., transferFunds, withdrawToBank, redeemRewards) and example GraphQL mutations that would perform ledger writes. It also references payment/banking providers (Plaid/Stripe/Dwolla/Marqeta) and testing patterns to trigger/verify actual ledger state changes (idempotency replay, double-spend), which are specific financial execution capabilities rather than generic tooling.