agent-wallet-desk

Warn

Audited by Snyk on Oct 30, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The workflow monitors and consumes outsider-authored free text from project websites, posts, and contract descriptions when researching URLs and instructions.

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

  • Direct money access detected (high risk: 0.70). The skill manages Binance Agentic Wallet multi-account operations, BSC positions, CA trading, and project mint/claim workflows. It supports direct financial operations such as buying, selling, minting, and claiming tokens or assets through wallet interactions and transaction submissions (e.g., lines 25, 43-45, 70-71, 76-78). However, access control for these direct financial operations relies solely on user confirmation within the local web interface and app prompts ("用户核对本笔预览后点击确认,服务才提交", "授权与 mint 必须分别用户确认"), without an independent service- or execution-layer authentication/authorization mechanism that validates the transaction outside of the agent workflow itself.

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
Oct 30, 2026, 09:55 AM
Issues
2