Browswer Automation
Warn
Audited by Snyk on Mar 13, 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 core workflow explicitly requires opening arbitrary URLs and interacting with page content via "agent-browser open " and "agent-browser snapshot", which exposes the agent to untrusted public web pages whose content it must read and act on.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata