hunt-write-gap

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). The presence of an external image hosted on "evil.com" (https://evil.com/pwned.png) used as an avatar URL is suspicious—external hosts can serve tracking, phishing content, or be swapped to deliver malicious payloads; api.target.com is just a placeholder API endpoint and not a download source.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document provides explicit, actionable instructions to exploit authenticated writeable endpoints for privilege escalation, financial manipulation, profile hijacking, and cross-user (IDOR) writes—clear guidance for malicious abuse.

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

• Direct money access detected (high risk: 1.00). The skill explicitly describes and demonstrates modifying account balances and creating financial "movements" via API calls (e.g., POST /movements with an "amount" field) and calls out "Balance injection" / "fake income" as a confirmed pattern. These are specific, financial-action endpoints (ledger/transaction creation and balance manipulation), not generic browser or API tooling, and therefore constitute direct financial execution capability.