ccxt-typescript
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources (cryptocurrency exchanges) and use that data within its execution context. When combined with its extensive trading and account management capabilities, this creates a potential surface for malicious data to influence agent behavior.
- Ingestion points: External market data, ticker information, order books, and event descriptions are ingested from exchange APIs via methods like
fetchTicker,watchTicker,fetchOrderBook, andfetchEvents(documented in SKILL.md). - Boundary markers: The provided code examples do not include explicit boundary markers or instructions to ignore embedded commands within the fetched API data.
- Capability inventory: The skill provides access to highly sensitive capabilities including order creation (
createOrder,createMarketOrder), order cancellation (cancelOrder), fund transfers (transfer), and withdrawals (withdraw), as well as API credential handling viaapiKeyandsecretparameters. - Sanitization: There is no evidence of data sanitization, validation, or escaping of the content received from external exchange APIs before it is processed or logged.
Audit Metadata