seo-roast
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly takes user-provided URLs and uses the Browser/Playwright MCP or the
agent-browserCLI to open, snapshot, and scrape page text/HTML/screenshots from public websites (and optionally uses a SERP API), thereby ingesting untrusted third-party web content.
Audit Metadata