skills/kotek-7/dotfiles/browser-use/Gen Agent Trust Hub

browser-use

Fail

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: HIGHDYNAMIC_EXECUTIONDATA_EXFILTRATIONCREDENTIALS_UNSAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill provides a high-risk interface for arbitrary code execution via the browser-use python command.
  • Evidence in references/cdp-python.md demonstrates that arbitrary Python statements can be executed in the host environment, with variables persisting across calls.
  • The browser-use eval command allows for the execution of arbitrary JavaScript within the browser context, enabling the manipulation of web pages and access to browser-scoped data like localStorage.
  • [DATA_EXFILTRATION]: Multiple commands facilitate the extraction of sensitive authentication data.
  • Commands such as browser-use cookies get, browser-use cookies export, and browser-use get value allow for retrieving session tokens and user inputs.
  • The browser-use screenshot command can capture sensitive information displayed on the screen.
  • [CREDENTIALS_UNSAFE]: The skill manages and accesses highly sensitive credentials.
  • It provides access to local Chrome profiles via the --profile flag, which contains the user's saved passwords, cookies, and browsing history.
  • Commands like browser-use cloud login and browser-use cloud signup involve the handling and storage of API keys in local configuration files (~/.browser-use/config.json).
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to interact with external, untrusted web content, creating a significant attack surface.
  • Ingestion points: browser-use open, browser-use state, browser-use get html, and browser-use get text fetch data from the live web into the agent's context.
  • Boundary markers: No explicit instructions are provided to the agent to treat fetched web content as untrusted or to ignore embedded instructions.
  • Capability inventory: The agent has access to powerful capabilities including arbitrary command execution (CLI), Python/JS execution, and network operations.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from web pages before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill utilizes a broad range of CLI commands that interact with the operating system, including starting daemons, managing network tunnels, and interacting with local browser installations.
  • [EXTERNAL_DOWNLOADS]: The browser-use profile update command initiates the download and installation of external binaries (profile-use) to the local system.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 9, 2026, 02:38 PM