browser
Warn
Audited by Snyk on May 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill explicitly navigates to arbitrary URLs and ingests page content (see SKILL.md commands like "navigate", "snapshot", "text", "get-dom" and the browser.mjs flows for observe-bundle / observe-actions which build observation bundles and rank next actions from snapshot/page text), so untrusted public web pages can be read and materially influence the agent's next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata