The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a Python script (resolve_customization.py) located within the project's _bmad/scripts/ directory using uv run. This occurs during both the initialization and completion phases to handle configuration logic.\n- [DYNAMIC_EXECUTION]: The workflow incorporates dynamic execution of instructions provided in configuration files (customize.toml and overrides). Specifically, it executes steps defined in activation_steps_prepend, activation_steps_append, and follows a terminal instruction from on_complete.\n- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests and processes various external artifacts such as GDDs, Epics, and Narrative documents.\n
Ingestion points: Project artifacts loaded from {planning_artifacts} and {project_knowledge} directories.\n
Boundary markers: The skill does not define specific boundary markers or use "ignore" instructions to prevent the agent from following directions potentially embedded within the ingested documents.\n
Capability inventory: The skill possesses capabilities for shell command execution (via uv) and file system writes.\n
Sanitization: There is no evidence of content sanitization or validation performed on the ingested project documentation before it is utilized in the workflow.

gds-correct-course