bmad-builder

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell scripts (scaffold-skill.sh, validate-skill.sh) for automation. These scripts include robust input validation, such as regex checks on skill names, and operate within the local project structure. This is standard behavior for developer-oriented tools.
  • [PROMPT_INJECTION]: No malicious instructions aimed at overriding agent behavior or bypassing safety filters were found. The skill's instructions are focused on enforcing project boundaries (e.g., 'Scope Law') and ensuring technical compliance.
  • [EXTERNAL_DOWNLOADS]: The skill does not perform any network operations or external downloads. All templates and validation scripts are provided as local files within the skill directory.
  • [DATA_EXFILTRATION]: No patterns indicative of data exfiltration or credential harvesting were detected. The skill uses environment-specific path variables (e.g., ${CLAUDE_PLUGIN_ROOT}) to manage local file system operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 12:30 PM
Security Audit — agent-trust-hub — bmad-builder