agent-browser-troubleshooting

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to download and install the Chromium browser shell using npx playwright-core. This targets a well-known package and service associated with Microsoft's Playwright project.
  • [COMMAND_EXECUTION]: The guide includes several shell commands for system configuration and diagnostics, such as networksetup for checking proxy settings and env -i for running the agent in a clean environment. These are used to resolve local connectivity and environment issues.
  • [PROMPT_INJECTION]: The skill facilitates the processing of arbitrary web content through the agent-browser tool. This creates a surface for indirect prompt injection where malicious instructions embedded in a web page could attempt to influence the agent's behavior.
  • [COMMAND_EXECUTION]: The skill uses agent-browser eval to execute JavaScript directly within the browser context. While this is a primary feature for data extraction and automation, it allows for dynamic code execution based on the page being visited.
  • [SAFE]: No hardcoded credentials, malicious persistence mechanisms, or obfuscation techniques were detected in the provided markdown file.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 04:53 PM