The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data by reading markdown and YAML files across the repository (e.g., production/epics/**/*.md, design/gdd/systems-index.md). This represents a potential surface for indirect prompt injection where instructions hidden in documentation could influence agent behavior.
Ingestion points: File read operations in Sections 2 and 3 targeting project documentation and story files.
Boundary markers: No specific delimiters or "ignore instructions" directives are defined for the content ingestion.
Capability inventory: The skill uses Read, Glob, Grep, and Task tools. It lacks network access or file-write capabilities.
Sanitization: No explicit sanitization of file content is mentioned before processing.

story-readiness