The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses uv run to execute a local Python script (resolve_customization.py) located within the project's _bmad/scripts directory. This occurs during the initial activation in SKILL.md and upon workflow completion in steps/step-06-final-assessment.md. This is an internal project tool used for merging configuration layers.
[INDIRECT_PROMPT_INJECTION]: The skill processes external project documentation (GDD, UX, Architecture, and Epics), which introduces a surface for indirect prompt injection if those files contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Document files located in the {planning_artifacts} directory, as discovered in steps/step-01-document-discovery.md.
Boundary markers: Absent; the instructions do not implement specific delimiters or 'ignore' instructions when reading the contents of project documents.
Capability inventory: The skill has the capability to execute local scripts via uv run and write report files to the local file system.
Sanitization: Absent; there is no evidence of filtering or escaping content read from documentation before it is analyzed or summarized in the output report.
[DYNAMIC_EXECUTION]: The skill supports a workflow.on_complete extension point in steps/step-06-final-assessment.md. This field is resolved from configuration files (customize.toml or overrides) and is followed by the agent as a terminal instruction, which could lead to the execution of arbitrary commands if the local configuration is modified.

gds-check-implementation-readiness