emblem-ai-agent-wallet

Warn

Audited by Snyk on Mar 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill and its documentation explicitly instruct the agent to fetch and use open third‑party web and social/market data (e.g., references/market_research.md: "Get the tokenomics details from Jupiter's website", references/capabilities.md: "Real-time Data Sources / social trend indicators", and the plugin/data-source integration notes), meaning the agent will read untrusted public content that can influence trading or tool actions.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly a crypto wallet/transaction tool. It connects to EmblemVault to manage wallets across multiple blockchains (Solana, Ethereum, BSC, Polygon, Hedera, Bitcoin), supports swaps, transfers, signing, limit/stop orders, DeFi operations (LP, yield farming), and provides CLI/agent modes and scripts to perform swaps and transfers. It includes programmatic/password auth for automation and examples like "Get a swap quote" and "Swap Tokens" scripts. These are specific crypto financial execution capabilities (wallet management, transaction signing, swap/order placement), not generic tooling.

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
Mar 16, 2026, 03:35 AM
Issues
2