The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted documentation files from the local workspace to generate user stories, creating an attack surface where embedded instructions could influence the agent's behavior.
Ingestion points: Reads documentation from docs/BRIEF.md, docs/research/*.md, and docs/screens/INDEX.md as specified in SKILL.md.
Boundary markers: No explicit delimiters or instructions are used to separate ingested data from agent instructions.
Capability inventory: The skill writes to docs/STORIES.md and invokes a ux-design tool. There are no subprocess executions, network operations, or access to sensitive system files.
Sanitization: The skill relies on the agent's default processing and does not implement custom sanitization for the ingested text.

user-stories