The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script located at {project-root}/_bmad/scripts/resolve_customization.py using the uv run command during the activation and completion phases.
[DYNAMIC_EXECUTION]: The workflow configuration supports the execution of arbitrary commands through the activation_steps_prepend, activation_steps_append, and on_complete hooks defined in customize.toml or project-level overrides.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted project data, including test source code, test execution results, and configuration files, creating a surface for indirect prompt injection.
Ingestion points: The agent reads project-level configuration files (_bmad/gds/config.yaml), customization overrides (_bmad/custom/{skill-name}.toml), and all project test files and results during the metrics gathering phase.
Capability inventory: The agent possesses the capability to execute shell commands via uv run and write report files to the local file system.
Boundary markers: The instructions lack explicit delimiters or warnings to the agent to disregard any natural language instructions discovered within the project files it reviews.
Sanitization: No sanitization, validation, or escaping of the ingested file content is performed before the data is processed by the agent.

gds-test-review