agent-browser
Warn
Audited by Snyk on Apr 23, 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 core workflow explicitly opens arbitrary URLs with "agent-browser open " and then uses snapshot, get text/get html, and eval to read and act on page content, so untrusted public web pages can materially influence subsequent clicks/commands.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata