web-visual-verification
Warn
Audited by Snyk on May 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's Playwright scripts explicitly navigate to a configurable URL (page.goto(process.env.URL || 'http://localhost:3000/')) and then evaluate DOM, console errors, and run assertions against that page—so it ingests and acts on content from arbitrary/deployed web pages (including public URLs in CI), which can materially influence pass/fail outcomes and follow-up diagnose actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata