browser-automation
Warn
Audited by Snyk on Apr 16, 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). SKILL.md explicitly instructs the browser-use Agent to navigate to and extract/interprete content from public third‑party websites (e.g., GEPIA2, GeneCards, TIMER2.0, HPA) as part of its workflow, so untrusted page content could materially influence the agent's actions and enable indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata