planetscale-schema-recommendations-agent-loop

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md describes an agent workflow that consumes “Open schema recommendations” and “Supporting Insights evidence,” which at runtime would typically be fetched from PlanetScale/Insights (outsider-authored public/vendor content) and then converted into LLM-readable text for planning.