layers-orient

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md the runtime workflow for /layers-orient only collects end-user design inputs via guided questions (e.g., “Describe your design situation…”, “What product or feature are you working on?”) and then uses that text for layer audit/bottleneck/recommendations, so outsider-authored free text is directly ingested.