web-scraping

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests content from arbitrary public websites and social media (e.g., RequestsScraper.fetch, TrafilaturaСscraper.fetch, PlaywrightScraper.fetch, yt-dlp for YouTube, instaloader for Instagram, and TikTok scrapers), and then reads/parses that untrusted, user-generated content (returned as ScrapingResult.content, captions, transcripts, etc.), which could enable indirect prompt injection.