gentic-creative-assets

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly scrapes web pages via fetch_page, queries a public Meta Ad Library via search_inspiration_ads, and accepts arbitrary public image URLs (e.g., inspiration_image_urls, brand_image_urls, image_url) which the agent reads and uses to influence ad/video generation, creating clear exposure to untrusted third-party content that can alter actions.