The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses dynamic context injection to execute ls production/sprints/ when loaded. This is used to discover existing sprint files and is considered a benign use of the feature.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests data from multiple project directories to generate plans.
Ingestion points: Reads files from production/milestones/, production/sprints/, design/gdd/, and production/risk-register/.
Boundary markers: None identified in the skill instructions.
Capability inventory: The skill has access to Write and Edit tools via the allowed-tools configuration.
Sanitization: No validation or sanitization of ingested content is performed before processing.

sprint-plan