The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script located at {project-root}/_bmad/scripts/resolve_customization.py during both activation and validation phases. This script is part of the vendor's internal framework used to merge project-level, team-level, and user-level configuration settings, representing standard and expected behavior for this environment.
[PROMPT_INJECTION]: The workflow involves an ingestion point where untrusted data is read from project epic files (*epic*.md) to extract work items. While this creates a surface for indirect prompt injection, the skill employs specific structural patterns (e.g., header-based parsing) for data extraction. The capability inventory is limited to writing status updates to a local YAML file and executing internal configuration scripts, and the lack of explicit boundary markers is mitigated by the skill's narrow scope and local-only operations.

gds-sprint-planning