browser-use
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the
browser-use pythoncommand, which enables the execution of Python statements to interact with the browser session. - [REMOTE_CODE_EXECUTION]: Provides recipes for executing JavaScript via
Runtime.evaluateand Python code that interacts with internal browser objects likebrowser._sessionandbrowser._runinreferences/cdp-python.md. - [CREDENTIALS_UNSAFE]: Documents how to extract browser cookies using the
Network.getCookiescommand, which provides access to sensitive session data. - [PROMPT_INJECTION]: The skill processes untrusted data from the browser (Ingestion: browser window content). While it includes boundary rules (Boundary: Rule 3 in
SKILL.md), it provides powerful execution capabilities (Capabilities: Python execution, JS evaluation inreferences/cdp-python.md). No explicit sanitization of web content is mentioned beyond high-level instructions to the agent (Sanitization: None).
Audit Metadata