marketing-carousel-growth-engine
Warn
Audited by Snyk on Apr 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly states the agent uses Playwright to navigate and scrape any target website URL (and internal pages like pricing, testimonials, about) via analyze-web.js and consumes that extracted third-party content to generate hooks, visuals, and publishing decisions, which could allow indirect prompt injection from untrusted web content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly uses Playwright at runtime to navigate and scrape arbitrary target website URLs (the user-supplied URL passed to analyze-web.js), and that scraped content is injected into and directly controls the Gemini slide-generation prompts, making those external sites a required runtime dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata