Agent Browser Operator
Warn
Audited by Snyk on Mar 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md Overview explicitly states the agent uses the OpenClaw browser tool to browse, interact with, and extract data from JavaScript-rendered and public/authenticated web pages (multi-step site navigation and logged-in flows), meaning it will fetch and interpret arbitrary third-party web content that could contain untrusted/user-generated instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata