brand-dev

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

• Third-party content exposure detected (high risk: 1.00). The skill's endpoints (e.g., /v1/brand/styleguide, /v1/brand/ai/query, /v1/brand/screenshot, /v1/brand/ai/products) explicitly crawl, scrape, and ingest content from arbitrary public domains, meaning untrusted third‑party website content is read and interpreted and can influence agent decisions.