market-data

Warn

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/full_function_smoke_check.py executes shell commands using subprocess.run(cmd, shell=True). The command string is constructed by directly interpolating user-controllable arguments such as --us-symbol and --hk-symbol. This allows for arbitrary command execution if an attacker provides stock symbols containing shell metacharacters (e.g., ;, &, |).
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to several external financial data sources and stock exchanges.
  • Evidence: The implementation fetches data from well-known and reputable services including Tencent (gtimg.cn), Sina (sinajs.cn), Yahoo Finance (yahoo.com), the Federal Reserve Economic Data service (stlouisfed.org), Nasdaq (nasdaqtrader.com), and the Hong Kong Stock Exchange (hkex.com.hk).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 4, 2026, 03:34 AM
Security Audit — agent-trust-hub — market-data