lifi-stablecoin-swap
Warn
Audited by Snyk on Jul 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The workflow repeatedly fetches outsider-authored free-form JSON from a public runtime endpoint (
fetch("https://order.li.fi/orders/status?...")inreferences/quickstart.mdand the/quote/requeststyle endpoint), which is then read into variables used to drive the agent/LLM context.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The SKILL.md describes a specific crypto payment/swap integration (LI.FI Intents) with concrete APIs and on-chain actions: it documents the TypeScript SDK and raw REST endpoints to request quotes, build StandardOrder structs, perform ERC-20 approve, and call open(order) on an InputSettlerEscrow contract (including example wallet.writeContract). It also lists contract addresses and the POST /quote/request and GET /orders/status endpoints. These are explicit blockchain transaction and funds-movement operations (wallet approves, on-chain open, escrow settlement), so this skill grants direct financial execution capability.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata