deepbook-margin

Warn

Audited by Snyk on Aug 21, 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 to query the Sui MCP server (https://sui.mcp.kapa.ai) and to fetch pages from docs.sui.io / the deepbookv3 GitHub repository at runtime for verification and up-to-date answers, so remote content will directly influence prompts and 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 on-chain margin trading and integration with the DeepBook SDK. It names and directs use of specific on-chain trading/borrowing operations (e.g., "deposit collateral, borrow funds, place margin orders, or withdraw") and references concrete SDK functions ("place_limit_order_v2", "place_market_order_v2") and MarginManager lifecycle. These are explicit crypto/blockchain transaction actions that enable moving assets and executing market orders, so this grants direct financial execution capability.

Issues (2)

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 21, 2026, 06:33 PM
Issues
2
Security Audit — snyk — deepbook-margin