The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from various local files, including project instructions (AGENTS.md, CLAUDE.md) and design documents (design/gdd/), to inform its planning logic. If these files are sourced from untrusted contributors, they could contain instructions designed to influence the agent's behavior.
Ingestion points: The skill reads AGENTS.md, CLAUDE.md, and all design documents in the design/gdd/ directory.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when reading these external files.
Capability inventory: The skill utilizes Write, Edit, and Task tools, providing the capacity to modify the filesystem and execute sub-tasks.
Sanitization: There is no evidence of sanitization or validation of the content retrieved from these local documents before it is processed by the agent.

sprint-plan