web-design-reviewer
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.72). Yes: in Step 2.1 the workflow navigates to a user-provided URL, then retrieves DOM structure/snapshots (and screenshots) from the visited page, meaning outsider-authored HTML/DOM content can be ingested into the LLM context for analysis (runtime web-content exposure).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata