mt5-robot-tester

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the subprocess module to launch the MetaTrader 5 terminal (terminal64.exe) and to manage its own process tree (e.g., using taskkill on Windows). These operations are essential for its stated purpose of batch-testing trading robots and are correctly scoped to paths provided by the user or discovered in standard installation directories.
  • [DATA_EXPOSURE]: The skill interacts with local files, including Expert Advisor binaries, configuration files, and strategy tester reports. All network operations are limited to a local HTTP server used for the dashboard, which is bound to 127.0.0.1 and protected by CSRF tokens to prevent unauthorized control from other local processes or websites.
  • [DYNAMIC_EXECUTION]: The skill dynamically generates .ini configuration files and .set parameter files for MetaTrader 5. This is a core part of the automation workflow and does not involve the execution of untrusted code or the use of dangerous functions like eval() or exec() on external data.
  • [REMOTE_CODE_EXECUTION]: The skill relies solely on the Python standard library and does not download or install external packages or scripts at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 10:40 AM
Security Audit — agent-trust-hub — mt5-robot-tester