agent-browser
Warn
Audited by Snyk on Jun 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Runtime path: the skill’s
agent-browser open <url>+ subsequentsnapshot/get text/get htmlcommands cause the agent to ingest browser-extracted page content (public web pages or arbitrary URLs provided by the operating user), which is outsider-authored free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata