agent-browser

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and provides instructions to install the agent-browser CLI tool from a repository managed by a well-known organization.
  • [PROMPT_INJECTION]: The skill manages potential indirect prompt injection from untrusted web data. 1. Ingestion points: External websites accessed via the open command. 2. Boundary markers: Optional AGENT_BROWSER_CONTENT_BOUNDARIES environment variable. 3. Capability inventory: Bash access, file writing, and network navigation. 4. Sanitization: Supports AGENT_BROWSER_ALLOWED_DOMAINS for navigation restriction and AGENT_BROWSER_ACTION_POLICY to limit high-risk interactions like JavaScript evaluation.
  • [COMMAND_EXECUTION]: Browser interactions are performed via a specialized CLI. Security is maintained through an action policy that can deny sensitive actions like eval, download, or network requests.
  • [CREDENTIALS_UNSAFE]: The documentation provides safe patterns for authentication, such as using environment variables and saving session state from files, explicitly warning against hardcoding secrets in scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 07:00 AM
Security Audit — agent-trust-hub — agent-browser