The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses uv run to execute local scripts located in {project-root}/_bmad/scripts/ for resolving customizations and configurations. It also executes git diff, git diff --stat, and gh pr view to gather information about repository changes.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data from the codebase, including diffs, pull request details, and project artifacts like sprint status files.
Ingestion points: Data is sourced from git diffs, the gh CLI output, and project-level files via the persistent_facts configuration.
Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the ingested data.
Capability inventory: The skill can execute commands via uv, git, and gh tools.
Sanitization: There is no evidence of input validation or content filtering for the data processed during the walkthrough.

bmad-walkthrough