ad-creative-intelligence

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

• Third-party content exposure detected (high risk: 0.85). Yes—this skill’s required workflow runs meta-ad-scraper and google-ad-scraper to scrape competitor ads, and the scraped ad copy/headlines/landing-page text (outsider-authored web content) is then collected for “Cluster & Analyze,” which feeds that free text into the agent’s LLM context.