Agent Browser
Warn
Audited by Snyk on Feb 17, 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 exposes the agent to arbitrary public websites via commands like "agent-browser open " and then ingests and reads page content through "snapshot", "get text", and "get html", allowing untrusted third-party (user-generated) content to be interpreted by the agent.
Audit Metadata