browser-use

Warn

Audited by Snyk on Mar 18, 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.md explicitly instructs the agent to navigate and extract data from public websites (e.g., "Go to amazon.com", "Go to bestbuy.com", and multi-step browsing examples), which requires fetching and interpreting untrusted third-party web content that can influence agent actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 08:19 AM
Issues
1
Security Audit — snyk — browser-use