original-design
Warn
Audited by Snyk on Jul 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: 0.85). Yes—Phase 1.5 and Phase 6 explicitly instruct runtime web browsing/fetching of inspiration pages (public web content from sites like Pinterest/Dribbble/Behance/Unsplash), whose extracted text/pattern notes are then summarized and fed back into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata