Browser Use Agentic Browser Control
Warn
Audited by Snyk on Jun 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill is a browser automation controller, and at runtime it can fetch and ingest arbitrary public web page text (outsider-authored free-form content) into the agent’s LLM context via the browser/extraction step when navigating to user-specified URLs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata