browser-automation
Warn
Audited by Snyk on Apr 9, 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 allows navigating to arbitrary web pages (e.g., "agent-browser navigate --url ...") and performing content extraction, executing JavaScript, clicking/filling elements and snapshots, so the agent will fetch and interpret untrusted public web content that can materially influence its actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata