daytona-chrome-cdp

Warn

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: Uses daytona exec to perform shell operations in the sandbox environment, including launching Chromium with the --no-sandbox flag, which disables critical process isolation.- [DATA_EXFILTRATION]: Configures the browser to listen for remote debugging connections on 0.0.0.0 and suggests using daytona preview-url to expose the port. This allows any entity with access to the preview URL to monitor or control the browser, potentially exposing session cookies and credentials during sign-in flows.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it interacts with untrusted web content while maintaining the ability to execute shell commands.
  • Ingestion points: Web page data retrieved via browser_snapshot and other navigation tools.
  • Boundary markers: None used to distinguish web content from system instructions.
  • Capability inventory: Shell command execution via daytona exec and browser control.
  • Sanitization: Content from the browser is processed without visible sanitization.- [EXTERNAL_DOWNLOADS]: Suggests installing browser binaries like chromium or google-chrome within the sandbox environment if they are missing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 28, 2026, 12:27 PM
Security Audit — agent-trust-hub — daytona-chrome-cdp