The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes content from User Story README files, architecture decision records (ADRs), and existing technical tasks to generate or update technical specifications. This creates a surface for indirect prompt injection where instructions hidden in the documentation could influence the agent.
Ingestion points: Reads content from docs/specs/user-stories/US-XXX-[nombre-corto]/README.md, existing TK-*.md files, and reference files in docs/adr/ or docs/specs/technical-docs/.
Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions for the data being processed from the repository files.
Capability inventory: The skill has the capability to perform file system writes to create or modify technical tasks, work unit catalogs, and agent internal memory files.
Sanitization: Absent. There is no explicit validation, escaping, or filtering of the text content extracted from the ingested files before it is processed or written back to the filesystem.

story-plan