designsetup

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

• Third-party content exposure detected (high risk: 1.00). The skill requires running /extract on arbitrary public sites (example: "/extract https://airbnb.com") and then loads/parses design-system/extracted/*/data.yaml (references/interactive-workflow.md STEP 0.2 and SKILL.md prerequisites), meaning untrusted, user-provided web content is ingested and directly influences style/theme selection and subsequent file generation.