Carousel Growth Engine
Warn
Audited by Snyk on Jul 23, 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—during “Phase 2: Research & Analyze” the agent runs
analyze-web.jswith Playwright to scrape the target website (public/outsider-authored page text), then uses the resultinganalysis.jsoncontent as inputs to Gemini-based slide prompt generation, which becomes free text in the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata