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 includes commands and examples that take and return secret values verbatim (e.g., filling passwords in CLI arguments like
fill @e2 "password123",set credentials user pass,cookies/get value), so the agent would need to handle and output secrets directly.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill directly navigates and scrapes arbitrary public web pages via commands like "agent-browser open " and "agent-browser snapshot/get text/get html", meaning the agent will fetch and read untrusted third‑party (user-provided/public website) content.
Audit Metadata