The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from markdown files within the project directory to perform UX validations, creating a potential vector for indirect prompt injection.
Ingestion points: As specified in Phase 2 and Phase 3, the skill reads content from design/ux/ files, .claude/docs/technical-preferences.md, design/accessibility-requirements.md, design/player-journey.md, and GDD documents.
Boundary markers: The instructions in SKILL.md do not include explicit delimiters or instructions to the agent to treat ingested content as data to be analyzed rather than instructions to be followed.
Capability inventory: The skill is restricted to the Read, Glob, and Grep tools as defined in the frontmatter of SKILL.md. It does not have access to tools for file writing, network communication, or shell command execution.
Sanitization: There is no evidence of content sanitization or validation before the data is interpolated into the agent's context.

ux-review