The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from various project files to generate sprint plans and status reports.
Ingestion points: Reads content from production/milestones/, production/sprints/, production/epics/**/story-*.md, design/gdd/, design/game-brief.md, and production/risk-register/.
Boundary markers: The instructions do not specify the use of delimiters or explicit 'ignore' warnings when interpolating content from these external files into the agent's context.
Capability inventory: The skill has permissions to write to the project directory (Write, Edit tools) and execute specific local shell commands (Bash tool).
Sanitization: No validation, escaping, or filtering is applied to the markdown content or status fields read from project artifacts before processing.
[DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the ! shell execution syntax to populate configuration and file listings at load time.
Evidence: Uses !bash "${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh" resolve_config ... to fetch project settings.
Evidence: Uses !ls production/sprints/ ... to identify existing sprint artifacts.
Analysis: These commands are utilized for operational efficiency to resolve the execution environment's configuration. They target project-local paths and do not incorporate user-supplied arguments into the shell command string.

sprint-plan