next
Warn
Audited by Snyk on Mar 9, 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's API route (app/api/browse/route.ts) and server actions call page.goto(url) on arbitrary provided URLs, fetching and returning content (titles, screenshots, accessibility snapshots) from untrusted public web pages, which could supply instructions that influence downstream agent behavior.
Audit Metadata