Carousel Growth Engine

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill explicitly performs automated scraping of target websites and sends extracted content and generated media to external services without seeking user consent, and it autonomously installs recurring execution (cron-style scheduling), which together create high-risk data exfiltration and persistence behavior suitable for abuse.

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text when it runs analyze-web.js/Playwright to scrape the user-supplied target website URL and extracts content (features, testimonials, stats, pricing, CTAs) into analysis.json for Gemini generation.