browser-use
Warn
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The
scripts/mcp-client.pyscript usessubprocess.Popenwithshell=Trueto execute commands provided via the--stdioargument. This creates a risk of command injection if the agent is manipulated into passing malicious strings to this parameter. - [REMOTE_CODE_EXECUTION]: The
scripts/start-server.shscript usesnpx @playwright/mcp@latestto download and execute the Playwright MCP server from the NPM registry at runtime. - [DYNAMIC_EXECUTION]: The skill includes tools such as
browser_evaluateandbrowser_run_codethat allow for the execution of arbitrary JavaScript and Playwright code within the browser session, as detailed inreferences/playwright-tools.md. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to browse and interact with external websites, which presents a significant attack surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent's context through tools like
browser_navigateandbrowser_snapshotinSKILL.md. - Boundary markers: None are implemented to distinguish between browser content and agent instructions.
- Capability inventory: The skill possesses capabilities for shell execution (
mcp-client.py), arbitrary script evaluation (browser_evaluate), and file system interaction (browser_file_upload). - Sanitization: There is no evidence of sanitization or filtering applied to content retrieved from the web.
- [DATA_EXPOSURE]: The
browser_file_uploadtool defined inreferences/playwright-tools.mdaccepts absolute file paths, which could be exploited to exfiltrate sensitive files from the host system if the agent is improperly instructed.
Audit Metadata