agent-browser
Warn
Audited by Snyk on Oct 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The agent skill uses browser automation (
agent-browser open <url>) to navigate to arbitrary URLs specified by the user or task, ingesting outsider-authored web page content at runtime via snapshots and text extraction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata