The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the gh (GitHub CLI) and git commands to perform its core functions. It executes commands such as gh auth status, git blame, and git log to extract repository metadata and diffs. These operations are scoped to the local repository environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources, specifically Pull Request descriptions, issue discussions, and commit messages.
Ingestion points: Pull request bodies, issue comments, and git commit messages are read into the agent context (SKILL.md, Execution steps 1 and 2).
Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the PR or issue text.
Capability inventory: The skill can execute shell commands (git, gh) and write files to the local disk (_bmad-output/rca-reports/).
Sanitization: There is no explicit logic to sanitize or escape the external text before it is analyzed by the LLM.
[DATA_EXPOSURE]: The skill explicitly instructs the agent to perform 'Direct attribution' by naming individuals who introduced defects. While this is a documented design principle of the skill, it involves processing and re-publishing PII (contributor names) from the git history into a new report format.

bmad-os-root-cause-analysis