agent-browser
Fail
Audited by Snyk on Feb 15, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt's examples and CLI usage explicitly show embedding sensitive values (e.g., fill @e2 "password123") so an agent following it would output secrets verbatim, creating exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill navigates to arbitrary URLs with commands like "agent-browser open " and ingests page content via "agent-browser snapshot", "get text", and "get html", meaning it reads untrusted public web pages into the agent's workflow and could enable indirect prompt injection.
Audit Metadata