Trading Best Practices

Warn

Audited by Snyk on Feb 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: 0.80). The skill's Research Workflow Step 1 and the included scripts/research_latest.sh explicitly direct the agent to perform web searches and review public sources (e.g., SSRN, arXiv, SEC/FINRA pages), meaning the agent would ingest and interpret open, untrusted third‑party content.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly focused on algorithmic trading practices and contains direct references to placing orders and execution behavior (e.g., "execute_order(symbol, quantity)", guidance on limit vs market orders, execution quality, position sizing and stop-loss logic). Although it doesn't name a specific payment gateway or bank API, it is specifically designed for trading (buying/selling assets) and includes code-level examples of order execution. That matches the "Market Orders (Buying/Selling stocks or assets)" criterion for Direct Financial Execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:26 AM