agent-browser
Warn
Audited by Snyk on Jun 22, 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). Outsider-authored free text is ingested when the workflow navigates to a runtime-supplied URL and then runs
agent-browser snapshot -i/agent-browser get text body, which extracts arbitrary page text from that external site into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata