help
Warn
Audited by Snyk on Feb 16, 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 Import flow explicitly asks for a help center base URL and then crawls/fetches public HTML pages (sitemap/main-page crawl, fetch HTML, extract article body and convert to markdown), meaning the agent will ingest arbitrary public web content which could contain untrusted/user-generated instructions.
Audit Metadata