sui-overview
Warn
Audited by Snyk on Jun 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent at runtime to query the external MCP server (https://sui.mcp.kapa.ai) for up-to-date answers and verification, so content fetched from that URL would directly influence and control the agent's responses.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is explicitly about the Sui blockchain and its on-chain asset operations: it describes coin transfers between addresses, programmable transaction blocks (PTBs) that can transfer objects, split and merge coins, and references Sui Stack primitives (Walrus, Nautilus, DeepBook) and DeFi use cases. Those are specific crypto/blockchain capabilities for moving and managing on-chain funds (wallets/coins, transaction composition, and orderbook/DeFi primitives), not generic tooling. Therefore it grants direct financial execution capability.
Issues (2)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata