meta-ads-audit

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

• Third-party content exposure detected (high risk: 0.75). During Phase 4 the skill performs a runtime website crawl via WebFetch (homepage/about/top landing pages) and merges the fetched free-form page text into meta/business-context.json, which is outsider-authored content that can contain indirect prompt-injection strings.