fincept-execution

Warn

Audited by Snyk on Apr 11, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests public third-party data (e.g., the Python analytics example uses yfinance to fetch Yahoo Finance market data and the Rust WebSocket adapter pattern connects to external provider URLs to normalize incoming market messages), and that external data is parsed and used in the agent workflow (analytics -> Rust IPC, normalized MarketMessage -> broker/executeTrade), so untrusted third-party content can materially influence actions.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly focused on a trading/finance platform (Fincept Terminal) and includes broker integration with an executeTrade API surfaced in the TypeScript context: "import { useBrokerContext } ... const { activeBroker, isConnected, executeTrade } = useBrokerContext();". That is a domain-specific function to place trades/market orders. Additionally, the skill includes market-focused WebSocket adapters and MarketMessage types (Ticker, OrderBook, Trade) and broker credential handling in the Rust self-review (credentials use broker_credentials.rs), all indicating explicit financial execution capabilities rather than a generic tool. Therefore it meets the "market orders / move money" criterion.

Issues (2)

W011
MEDIUM

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

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 11, 2026, 06:19 PM
Issues
2
Security Audit — snyk — fincept-execution