bmad-customize

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local Python scripts for core functionality. It executes list_customizable_skills.py to identify installed skills that support customization and resolve_customization.py to verify that written overrides are correctly applied. These executions are restricted to the local environment and the skill's own project structure.
  • [DATA_EXPOSURE]: The discovery script reads metadata (descriptions) and configuration definitions (customize.toml) from other installed BMad skills to present customization options to the user. This is an intended feature and does not involve exfiltrating data to external services.
  • [SAFE]: The skill's test suite includes calls to subprocess.run to verify the command-line interface of the utility scripts. These calls are part of standard unit testing procedures and are executed securely without using shell interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 05:26 PM