The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing content from local documentation files to generate its output.
Ingestion points: The skill reads various local markdown files including GDDs (design/gdd/*.md), ADRs, and architecture documents in Step 2b.
Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands within the ingested text.
Capability inventory: The skill has the ability to write to the local filesystem using the Write tool and spawn sub-tasks using the Task tool.
Sanitization: There are no explicit sanitization or filtering steps defined for the content extracted from the source documents.
[COMMAND_EXECUTION]: The skill utilizes the Task tool to execute external review processes.
Evidence: Step 4b instructs the agent to spawn a producer task via the Task tool using the PR-EPIC gate to assess the validity of the proposed epic structure.

create-epics