The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes Volcengine's official CLI tool ('ve') via a Python wrapper script ('scripts/compliance.py'). The script uses subprocess calls with argument lists rather than shell strings, which prevents command injection. The operations are limited to the 'config' subsystem of the vendor's CLI.
[SAFE]: The skill implements a robust security boundary for write operations. Any action that modifies account configuration, such as deploying a compliance pack or enabling a configuration recorder, requires an explicit '--confirm' flag from the user. The skill is designed to perform a 'dry-run' first to show the user exactly what will be changed.
[SAFE]: Data handling is restricted to local processing and report generation. The skill reads compliance metadata from the Volcengine API and generates Markdown, CSV, and JSON reports in a local temporary directory. The instructions and code explicitly include measures to avoid including sensitive credentials like Access Keys or Secret Keys in any generated reports.

volcengine-compliance