tabbit-devtools
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
- [DATA_EXFILTRATION]: The skill reads the
DevToolsActivePortfile from Tabbit's user data directories. This file contains the sensitive debugging port and browser path required for remote control. - Evidence:
read_active_port_filefunction inscripts/discover_tabbit_cdp.pysearches%LOCALAPPDATA%,%APPDATA%, and~/Library/Application SupportforDevToolsActivePort. - [COMMAND_EXECUTION]: The skill executes external tools to perform browser automation.
- Evidence:
subprocess.run(command)inscripts/run_agent_browser_on_tabbit.pyis used to launch the browser automation client. - [INDIRECT_PROMPT_INJECTION]: The skill processes live web content through a browser, which creates a vulnerability surface for instructions embedded in web pages to influence the agent.
- Evidence: The skill is designed to visit and inspect URLs using
agent-browser(e.g.,open <url>inSKILL.md). - [DYNAMIC_EXECUTION]: The skill uses dynamic loading to execute its internal helper scripts.
- Evidence:
runpy.run_pathis used inscripts/read_current_tabbit_page.pyto executediscover_tabbit_cdp.py. - [EXTERNAL_DOWNLOADS]: The skill may download the
agent-browserpackage from a public registry if it is not already installed. - Evidence:
npx --yes agent-browseris used as a fallback execution method inscripts/run_agent_browser_on_tabbit.py.
Audit Metadata