browser-use
Warn
Audited by Snyk on Jul 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). At runtime the agent uses Playwright to load arbitrary web pages from the user-specified task (e.g., “Go to google.com…”), then feeds the resulting DOM snapshot/page text into the LLM context for evaluation, which is outsider-authored free text from public web content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata