Browser Use

Warn

Audited by Snyk on Feb 16, 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 agent-browser and browser-use agent explicitly open and scrape arbitrary public websites (e.g., agent-browser open "", get text/get html and the README example "Go to news.ycombinator.com"), so the agent will read and interpret untrusted, user-generated web content allowing indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:43 AM