weex-monitor-skill

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The main CLI script (scripts/weex_monitor_cli.py) utilizes subprocess.run to call specialized scripts in the sibling weex-trader-skill directory. This is the intended architecture for delegating sensitive data collection and order submission to a trusted execution boundary.
  • [SAFE]: The skill enforces a multi-step confirmation process. It generates unique confirmation tokens and requires users to respond with specific localized keywords ('确认' or 'confirm') before a monitoring task can be activated or a live loop started.
  • [SAFE]: The skill maintains a 'no-credentials' posture, intentionally avoiding the storage or direct use of API keys, instead relying on the weex-trader-skill for authenticated operations.
  • [SAFE]: The Task DSL and incoming exchange data are subject to normalization and validation (e.g., in normalize_task and evaluate_pnl_task), ensuring that only valid PnL metrics and authorized symbols are processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:51 PM
Security Audit — agent-trust-hub — weex-monitor-skill