digital-archive
Warn
Audited by Snyk on May 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The workflow's process_url explicitly calls self.scraper.fetch(url) (ScrapingCascade) to scrape arbitrary web/social URLs, then feeds result.content/result.text into the AI categorizer and entity extractor which directly influence downstream actions (categories, summaries, entity/relationship creation, PDF generation, and sheet updates), exposing the agent to untrusted third-party content that could carry indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata