The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting user-supplied data to generate project configurations.
Ingestion points: User inputs for project_name, project_type, and project_level are collected during the /workflow-init process.
Boundary markers: There are no explicit delimiters or boundary markers mentioned to isolate user-provided strings from the rest of the configuration instructions.
Capability inventory: The skill has file-writing capabilities, specifically creating and writing to bmad/config.yaml and docs/bmm-workflow-status.yaml.
Sanitization: The instructions do not define any sanitization, validation, or escaping logic for the project metadata before it is written to the file system.

BMad Master