finance-district

Fail

Audited by Snyk on Mar 31, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to ask the user to share an 8-digit email OTP and then run commands like fdx verify --code <OTP>, which requires embedding the secret OTP verbatim into the agent's output/commands.

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

  • Third-party content exposure detected (high risk: 0.90). The skill's x402 payment workflow instructs the agent to call arbitrary resource servers (see "x402 Payments" in SKILL.md and references/x402-payment-flow.md) and to read and act on the returned HTTP 402 JSON (accepts[] payment options), meaning untrusted third-party responses can directly influence which payment authorizations the agent signs and sends.

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

  • Potentially malicious external URL detected (high risk: 0.90). The x402 workflow explicitly instructs the agent to call arbitrary resource-server URLs at runtime (the resource server endpoint used in the x402 flow, e.g. https://api.example.com/protected-resource) and the returned HTTP 402 PaymentRequired JSON directly determines which payment authorization the agent must sign, so that external URL content controls agent actions.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly and primarily designed to perform financial operations. It exposes a CLI for crypto wallet management (create/setup wallets; send/receive/transfer tokens; swap/trade/exchange; stake, deposit/withdraw from DeFi vaults; bridge tokens; check balances/portfolio; pay for services via x402) and a payment gateway (Prism) to manage merchant accounts, Points of Service, API keys, settlement wallets, payment history, and earnings. It includes commands that authorize and execute payments (e.g., authorizePayment, swaps with --mode Execute, transfer execution) and merchant payment management. These are concrete, purpose-built financial actions (crypto transactions and payment gateway operations), not generic tooling, so they provide 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
Mar 31, 2026, 07:34 AM
Issues
4
Security Audit — snyk — finance-district