browser-tools
Warn
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill introduces a
skills getcommand that allows the agent to fetch and install third-party capability packs from remote sources. It also includes anupgradecommand for self-updating via package managers like npm or Homebrew. - [COMMAND_EXECUTION]: The tool relies on a wide array of shell commands executed through the
agent-browserbinary, includingbatchprocessing of commands from standard input and the ability to execute arbitrary JavaScript usingeval. - [DATA_EXFILTRATION]: Several capabilities present risks of sensitive data exposure. The
clipboard readcommand can access the host system's clipboard contents. Thenetwork harcommand captures full network logs which often contain authentication tokens. Additionally, theinspectcommand opens a local proxy for DevTools, which increases the network attack surface. - [REMOTE_CODE_EXECUTION]: The
skills getfunctionality acts as a vector for remote code execution by allowing the dynamic download and loading of external code modules or capability packs.
Audit Metadata