The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a Python script at {project-root}/_bmad/scripts/resolve_customization.py using uv run during the activation process. This represents a shell command execution surface directed by the skill instructions.
[DYNAMIC_EXECUTION]: The skill instructions define 'activation_steps_prepend' and 'activation_steps_append' (Step 2 and Step 7) which are retrieved from configuration files and executed in order. This mechanism allows for the execution of arbitrary actions defined in external YAML/TOML configuration.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect injection surface by ingesting data from multiple external sources.
Ingestion points: Reads configuration from {project-root}/_bmad/cis/config.yaml and persona overrides from {project-root}/_bmad/custom/{skill-name}.toml and {project-root}/_bmad/custom/{skill-name}.user.toml. It also loads 'persistent_facts' which can include contents from file glob patterns.
Boundary markers: None identified in the provided instructions to distinguish between internal instructions and external data.
Capability inventory: Includes subprocess execution via uv run and execution of dynamic activation steps.
Sanitization: No explicit sanitization or validation of the loaded configuration or file contents is described before they are adopted as instructions or facts.

bmad-cis-agent-storyteller