visual-style
Warn
Audited by Snyk on Nov 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The Extract mode's required workflow fetches a user-supplied website URL (from-website.md step 2, "Use web fetch to get the HTML/CSS"), so the agent ingests outsider-authored page text and CSS only after the user selects a specific arbitrary URL, which is a low-risk pull path rather than a monitored feed.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata